Implicit Bias

While gender and racial biases in language models have been widely studied, anti-LGBTQ biases remain underexplored, particularly beyond English. Existing benchmarks often do not capture cultural and linguistic variation and rely on gender representations. This paper introduces a multilingual German-English benchmark dataset for the evaluation of anti-LGBTQ biases in language models. It combines community-sourced stereotypes from German-speaking queer individuals with a German translation of WinoQueer. The data is used to evaluate eight language models across sizes and architectures and explore mitigation through fine-tuning on community and progressive media content. Results show that language models reproduce anti-queer stereotypes, with variation across identities and models. Differences between the translated and community-based data highlight the importance of cultural adaptation for multilingual bias evaluation. Fine-tuning reduces bias on average, but not consistently across models and identities. Warning: This text contains examples of anti-queer hateful language and stereotypes.

Long-tailed distributions are prevalent in real-world semi-supervised learning (SSL), where pseudo-labels tend to favor majority classes, leading to degraded generalization. While many long-tailed semi-supervised learning (LTSSL) methods have been proposed, the mechanisms by which they implicitly debias logits remain poorly understood. In this work, we revisit LTSSL through the lens of learning dynamics and provide a theoretical characterization of logits debiasing. Specifically, we derive a step-wise decomposition of the logits updates, showing that predictions are dominated by class-imbalance bias that reliably reflects label priors. To expose this effect, we use the logits of a task-irrelevant baseline image as an indicator of accumulated bias and prove that they converge to the class prior. This provides a unified view where LTSSL remedies such as logit adjustment, reweighting, and resampling correspond to reshaping gradient dynamics. Based on this insight, we propose DyTrim, a principle-based dynamic pruning framework that reallocates gradient budget through class-aware pruning on labeled data and confidence-based soft pruning on unlabeled data. We provide theoretical guarantees that DyTrim reduces class bias and improves generalization. Extensive experiments on standard LTSSL benchmarks show consistent gains across architectures and methods. Code available at: https://jiajun0425.github.io/DyTrim

Synthetic data is increasingly used to train large language models (LLMs), yet its security implications remain poorly understood. Prior work on subliminal learning suggests that models can inherit behavioral traits from seemingly unrelated training data. In this work, we investigate whether such mechanisms can be exploited to inject targeted social biases into aligned models through semantically benign synthetic data. We construct a pipeline in which a misaligned teacher model generates filtered synthetic datasets across domains such as creative writing and code generation, which are then used to fine-tune aligned student models. Our experiments show that benign-looking synthetic data can act as a covert channel for transmitting targeted biases while largely preserving the student model's general task capabilities. These results reveal a previously underexplored security risk in synthetic data-driven LLM training pipelines and highlight the need for improved safeguards. As one possible step toward this goal, we suggest that log-linearity-based scoring may provide a useful signal for screening seemingly benign synthetic data.

The language a legislature uses to debate women's rights, even in favour of them, encodes systematic patterns of sexism that persist across two centuries. In this work, we analyse 6,531 speeches over 200 years of UK parliamentary debate (Hansard, 1803-2005) by using large language models to classify a speaker's perspective towards women's suffrage and political representation, as well as analyse sexist speech in parliament from the lens of the Ambivalent Sexism Inventory. We also release this parliamentary dataset, an organized and metadata-enriched version of the publicly available Hansard Corpus optimized for computational social science research, with 6.7 million speeches across 1.2 million debates, with 89% gender-matching for speeches by MPs from the House of Commons. We find that 54% of speeches opposing women's representation contain sexist content, compared to 21% of speeches that are for the cause, and that the two sides use fundamentally different types of sexism: anti-suffrage rhetoric combines hostile and benevolent framing, while pro-suffrage sexism is overwhelmingly benevolent. Female MPs support women's political rights at 93% compared to 70% for male MPs, a gap that closes only after enfranchisement. Our findings are evidence that benevolent and hostile sexism are used in different rhetorical contexts in a manner consistent with the theory of Ambivalent Sexism.

Defeasible reasoning is a type of reasoning where inferences are drawn from plausible current evidence, but can be retracted upon the introduction of newer evidence. Although recent studies have examined language-model behaviors in defeasible reasoning, the datasets have been static and lack wide coverage of non-monotonic reasoning categories. We introduce DeReLab, a generative framework that produces multi-turn belief-updating conversations from parameterized graph structures across default and inheritance reasoning, with formally verified ground truth at every turn, enabling controlled measurement of how models respond to confirming and disconfirming evidence. This controlled generation process creates a testbed for experimental designs that isolate specific reasoning demands. Applying this capability to the study of confirmation bias, we evaluate nine open and proprietary large language models and find that nearly all exhibit a systematic tendency to accept congruent evidence while resisting incongruent updates, with several models correctly identifying a weakening update yet failing to revise their conclusion. We believe our work and findings will facilitate future research on evaluating language models in defeasible reasoning.

In pointwise document reranking, Chain-of-Thought models typically underperform direct scoring models. While existing diagnostics attribute this to inferior classification, score polarization, or calibration breakdown, whether targeted training can bridge this gap remains unclear. Our empirical study first confirms that this gap is stable across scales up to 32B parameters, ruling out model and data capacity confounders. We then apply stress tests utilizing reinforcement learning, fine-grained supervision, and architectural decoupling to explicitly repair these deviations. Although these interventions improve classification accuracy and absolute scores, the relative ranking gap persists. These findings suggest that, within the pointwise scoring paradigm, routing continuous relevance semantics through discrete text constrains ranking signal resolution, revealing a bottleneck that is stable and difficult to overcome under current standard methods, rather than an easily resolvable training bias.

Large language models (LLMs) demonstrate strong Helpfulness, Harmlessness, and Honesty (3H) alignment in English-centric settings, but these gains transfer poorly to low-resource languages due to cultural mismatches. Existing multilingual 3H benchmarks rely predominantly on automated translation or LLM based synthesis, propagating source-language biases while sacrificing local relevance. To address this gap, we introduce Pak3H1, the first human-validated, culturally contextualized Urdu benchmark suite for 3H alignment, comprising PakAlpaca (helpfulness), PakBeaverTails (harmlessness), and PakTruthfulQA (honesty). Our multi-stage pipeline integrates manual cultural adaptation and dictionary-guided post editing to prioritize native speaker judgment, ensuring both semantic fidelity and contextual authenticity. Zero-shot evaluations across multiple open and proprietary LLM architectures reveal systematic cross-lingual alignment gaps: helpfulness win rates decline under localized contexts, harmlessness guardrails break down against regional safety risks, and composite honesty metrics degrade substantially due to localized factual constraints. These findings expose structural limitations in current alignment approaches, underscoring the necessity of human-guided localization for equitable multilingual evaluation.

Text-to-image models learn associations between concepts - in the case of this paper, people's professions, which we refer to as roles - and visual attributes. These associations can underpin many observed forms of stereotypical bias. A key open question in this area is whether these associations are stable or change when visual representations of people in professional roles are placed in different prompted contexts. We introduce ContextBias, a controlled evaluation framework, and ContextBench, a benchmark spanning 92 roles and 1,656 semantically controlled prompts, designed to isolate the effect of contextual variation on role-linked visual representations. Evaluating four state-of-the-art models on 66,240 generated images, we find that placing a role in a semantically unrelated context does not suppress role-linked attributes; instead, cross-role attribute concentration increases (pooled BI $+0.047$). Demographic cues, characteristic garments, and role-specific tools remain highly prevalent across context-free, related, and unrelated conditions, and are robust to semantic prompt reformulation. Scene composition and camera framing show the greatest context-sensitivity. These findings reveal a form of stereotypical persistence that remains largely invisible to context-free evaluations, highlighting the need for controlled contextual variation in bias benchmarking. Code and dataset: https://huggingface.co/datasets/shaghayegh/ContextBias , https://github.com/Sina-Emami/ContextBias

Media bias detection relies on definitions and examples that specify what counts as bias, yet these specifications often vary across datasets or remain implicit, even when given the same name. Such variation makes it unclear whether models trained for the same bias category learn the same construct or different phenomena, a problem largely overlooked in prior work. We examine how definition choice affects bias annotation in a between-subjects experiment with 354 participants and a parallel evaluation with four LLMs. Participants and models rate six news articles across four bias categories using definitions that vary in conceptual framing and elaboration. Across 8,496 human and 28,800 LLM ratings, we find that the conceptual target of a definition drives annotation divergence, while construct-preserving elaboration does not: conceptual framing significantly shifts annotations for humans and does so even more strongly for LLMs. We discuss implications for construct specification in annotation protocols and prompt-based measurement, and consider how definitional sensitivity may propagate to downstream classification beyond media bias. We also release MUDD, the Multi-Definition Bias Detection Dataset.

Search rankings are valuable because human attention is scarce and sequential. Higher-placed alternatives are easier to find, so they are examined and bought more often. Consumers are now delegating search to AI agents that can ingest an entire results page at once. Randomizing the order of one hundred hotel listings across 5,000 AI agent sessions, we compare four large language models against human field data. AI agents search more deeply than humans and never decline to buy. Position still predicts which listings are inspected, but weakly and non-monotonically: the middle of a results page has the lowest probability of inspection, not the bottom. Position reaches the choice stage for some models and not others, a heterogeneity that tracks neither provider nor capability. All models nonetheless converge on the same undominated listing. For agentic search, the attributes displayed on a results page matter more than placement within it.

Professional communication is increasingly mediated by LLMs - but do these models serve all users equally? We show that when prompts contain linguistic features more commonly used by women (hedges, tag questions, collective reference), they systematically elicit shorter, less sophisticated, and less formal responses across three document types and four models. These effects persist after controlling for prompt complexity and feature carry-over. Explicit gender cues like sign-off names are encoded in the same representational space as linguistic dialect - suggesting shared underlying mechanisms - yet linguistic register is far more influential, producing large, consistent effects where names produce none. Our results further reveal that post-hoc mitigation is challenging: because these patterns are culturally embedded and outside conscious control, users cannot easily avoid them through strategic self-presentation, and mechanistic analysis reveals that linguistic features are encoded in early transformer layers and entangled with other features. Our work calls for upstream consideration of the influences of linguistic variation to mitigate disparate impacts of LLM-mediated workplace communication.

The Naive Bayes (NB) classifier remains a standard choice for categorical data, yet its widely used smoothing rules, such as Laplace, Lidstone, Krichevsky-Trofimov, and the $m$-estimate, all prescribe a fixed smoothing strength that ignores feature cardinality, sample size, and class imbalance, inducing a non-vanishing bias on modern high-cardinality tabular data. We propose hierarchical empirical-Bayes Naive Bayes (HEB-NB), in which each class-feature conditional probability is smoothed by a Dirichlet prior whose concentration is learned data-adaptively via Type-II maximum likelihood, enabling principled information sharing across classes while retaining closed-form inference. We further introduce HEB average one-dependence estimators (HEB-AODE), showing that the adaptive smoothing transfers cleanly to structural relaxations of NB. Theoretically, we establish a non-asymptotic $\ell_1$ error bound for HEB-NB matching the empirical-distribution minimax rate plus a vanishing data-adaptive bias, together with a matching Laplace-tight lower bound that yields a finite-sample, risk-level strict separation from Laplace. We further derive a plug-in excess Bayes-risk bound via total-variation tensorization and a population top-1 expected calibration error (ECE) corollary. Empirically, across 31 UCI and OpenML benchmarks, HEB-NB attains the best average Friedman rank on probabilistic metrics, with up to 22.1% log-loss reductions on high-cardinality datasets and consistent improvements of HEB-AODE over vanilla AODE. Combining HEB-NB with mutual-information weighting reduces top-1 ECE by 41%-70%, demonstrating substantial gains in probabilistic accuracy and calibration.

As Large Language Models (LLMs) are increasingly deployed as autonomous agents, accurately evaluating their latent values and biases is critical. The NLP community typically evaluates models using large, unstructured benchmarks. While effective for general capabilities, these datasets fundamentally conflate causal mechanisms: even when an aggregate bias is detected, unstructured evaluations cannot disentangle whether it stems from baseline traits, contextual confounders, or complex interactions. To address this, we introduce an analytically exact framework for the controlled behavioral evaluation of LLMs. We bridge human psychometrics with LLM mechanics by resolving gaps in design, measurement, and analysis. First, we replace unstructured prompting with fully crossed factorial experiments to systematically isolate causal main and interaction effects. Second, we eliminate Monte Carlo text sampling noise by operating directly on exact, token-level Probability Mass Functions (PMFs). Third, we derive a multivariate ordinal consensus metric and a distributional ANOVA to process these PMFs analytically. We validate our framework with a case study on consumer ethnocentrism across five LLMs, demonstrating how our approach isolates systemic country-of-origin biases that aggregate benchmarks otherwise obscure.

In this project, we delved into the pervasive challenge of bias detection within the text content. More specifically, our focus lies on the identification of subjective bias, a type of bias that introduces improper attitudes or portrays a statement at odds with the actual truth. The subjective bias can jeopardize the authenticity and reliability of texts, leading to misconceptions and potential social tensions, especially when expressed through offensive language. Following prior work [1], we tackled with three different types of subjective biases in text: (1) framing bias with the use of one-sided words or phrases containing a particular point of view; (2) epistemological bias which includes subtle linguistic features that can affect the believability of the texts; (3) demographic bias with word/phrase usage under presuppositions of a particular demographic factor (i.e., gender or religion). In terms of the data we utilize, the input consists of texts that may harbor subjective biases. The output is a classification or annotation that reveals the presence or absence of such biases within the provided content. More specifically, we detected three different types of multi-span biases in corpus WIKIBIAS [2] with more than 4,000 sentence pairs from Wikipedia edits. The data is labelled by bias type for span pairs with the following categories: (1) framing bias, (2) epistemological bias, (3) demographic bias, and (4) no bias. The project codes are released at https://github.com/HoningJade/LLM-Bias-Type-Classification.

Large language models (LLMs) are increasingly integrated into healthcare, education, public services, and everyday decision making. They should provide comparable assistance regardless of a user's literacy, communication style, or prompt-engineering expertise. However, existing research on prompt robustness primarily focuses on adversarial attacks, prompt injection, and prompt optimization, while overlooking whether semantically equivalent requests receive different responses simply because they are phrased differently. We refer to this accessibility challenge as "Prompt Privilege": users with greater prompting expertise systematically obtain better model performance despite expressing the same underlying intent. To address this problem, we present a unified framework for measuring and mitigating accessibility disparities in LLM interactions. We introduce Prompt Equity Score (PES), a quantitative metric for evaluating performance consistency across user populations, and Prompt Equity Transformer (PET), an LLM-based agent that automatically transforms user requests into semantically equivalent, accessibility-oriented prompts while preserving their intent. PET shifts prompt optimization from the user to the AI system, functioning as an intelligent accessibility layer between users and foundation models. Experiments on the MedQA benchmark demonstrate measurable prompt privilege, with statistically significant performance disparities between low-literacy and expert-prompting cohorts. Applying PET eliminates these disparities while preserving semantic fidelity, demonstrating that accessibility-oriented prompt normalization can improve equitable AI access. By introducing prompt privilege as a new dimension of AI accessibility and PET as a practical solution, this work advances system-centered accessibility and provides a foundation for more fair, trustworthy, and inclusive AI systems.

Reggaeton is one of the most widely consumed music genres in the world, and its lyrics are commonly regarded as highly sexualized. This claim rests mostly on qualitative studies and on small-scale quantitative ones. This paper has two goals. First, we present a reproducible method that uses a large language model to quantify thematic content in song lyrics along several independent dimensions. The method is not restricted to sexual content. Second, we apply it to a corpus of 1,259 songs by 12 reggaeton artists released between 2002 and 2025. The analysis covers four topics: a dataset characterization, a per-artist comparison, an analysis of how the dimensions change over time, and a comparison between our sexual-explicitness score and Spotify's own explicit flag. We release the data collection code, the scoring prompt, and the corpus, so that other researchers can replicate the approach or apply it to their own lyrics datasets.

The current work developed seven Retrieval-Augmented Generation (RAG) models based on leading deception theories and compared how deception judgments were made relative to baseline models. Across 700 statements drawn from five published deception datasets, four large language models (gpt-4o, claude-sonnet-4-6, ollama/llama3, deepseek-v4-flash), and two run-types (RAG vs. baseline), a total of 39,200 deception judgments were rendered. Detection accuracies were consistent with typical human accuracies and not statistically different across RAG (54.5%) and baseline models (54.6%). RAG-based models (57.0%) were less truth-biased than baseline models (59.7%), but the effect size was quite small. Theoretical perspective mattered little for accuracy yet mattered substantially for response bias, which ranged from highly lie-biased (the verifiability approach, 32.2%) to highly truth-biased (truth-default theory, 88.1%). Content effects and model effects further moderated the results. Theory-guided AI judgments are unreliable with current parameters, yet they might show promise with additional datasets, model testing, and theory-to-data matching.

Large language models are increasingly used for ordinal classification, yet semantically equivalent changes to prompt organization can alter their predictions. We conduct systematic experiments to characterize positional bias from label order, demonstration order, and demonstration placement. First, we apply the three probes to ten frontier LLMs on a common ordinal-classification task; every model is sensitive to all three positional sources, showing that the problem is pervasive. Second, we vary eight prompt-, task-, and model-level factors across five datasets; accuracy and stability are often misaligned, and only lower scale cardinality consistently improves both. Third, we compare pointwise, pairwise, and listwise inference, alternative aggregation and debiasing methods, and joint configurations; the tested corrections do not provide a reliable remedy, while a comparison-based listwise formulation offers the best balance but transfers unevenly across models and bias sources. These findings show that positional robustness depends on the full system configuration rather than the model alone. Ordinal-classification systems should therefore be selected jointly for predictive performance and stability.

Machine translation (MT) systems often fail to correctly translate gender, especially when converting from a gender-neutral language like English to a gendered target language such as Romanian. This bias results in translations that default to masculine forms or reinforce gender stereotypes. We propose a hybrid pipeline to mitigate this issue by combining large language model (LLM)-based gender classification with neural machine translation (NMT). Our system uses a fine-tuned LLM to detect the intended gender of target words in English sentences and insert inline gender hint tags. These tagged sentences are then passed to a Transformer model fine-tuned to generate morphologically correct Romanian translations. To support this, we introduce three novel datasets for gender disambiguation and translation. Our approach improves gender accuracy on the WinoMT and WinoGender benchmarks by over 40 percentage points compared to a baseline MT system. This is the first method to explicitly address and evaluate gender bias in English-Romanian MT using both LLM inference and tag-aware translation.

Fairness audits for LLM-based recommenders have largely focused on observable outputs, implicitly assuming that stable recommendations reflect stable internal processing. We challenge this assumption with FairGap, the first benchmark to jointly evaluate recommendation fairness at two levels: observable output shift (OBS) and hidden representation shift (IBS), measured through controlled counterfactual identity probes across gender, age, and race. Their relationship is summarized via Representation-Output Alignment (ROA), with quadrant diagnostics for identifying user-level hidden-output mismatch. Applied to six open-weight LLM families across three domains, FairGap reveals pervasive hidden-output decoupling: ROA rarely exceeds 0.22, and a non-negligible user population shows stable outputs despite substantial internal shifts, a mode that output-only audits cannot detect by design. Further, activation steering that reduces IBS by up to 8x simultaneously worsens OBS, demonstrating a fundamental tension between internal and output-level fairness that existing frameworks are unequipped to diagnose.

Data-centric curation pipelines frequently rely on model confidence scores to flag and filter noisy or mislabeled training instances. Evaluating this filtering convention on a large-scale consumer lending sample (LendingClub, N = 1,344,936) uncovers an underlying demographic asymmetry: high-income defaulters are disproportionately classified as label noise relative to low-income defaulters (Cramer's V approximately 0.03-0.07). Re-examining this behavior through the lens of equal opportunity [Hardt et al., 2016] reveals a far more severe discrepancy: a 16.86 percentage point gap in true positive rate (recall) between high- and low-income borrowers who ultimately defaulted. Implementing a sequential feature-blinding methodology allows us to isolate the drivers of this disparity across three distinct mechanisms: (1) direct reliance on self-reported applicant income; (2) algorithmic absorption of upstream institutional bias encoded within origination interest rates; and (3) a residual disparity (3.55 percentage points in cross-validation; 2.56 percentage points on a held-out test partition, Z = -4.04, p < 0.0001) that remains even after purging both income and interest rates from the model. Out-of-sample signed SHAP valuations demonstrate that this residual gap is maintained by structural proxies, most notably loan amount and home ownership status. These empirical findings show that simply blinding an algorithm to sensitive attributes fails to ensure fairness when institutional pricing decisions and behavioral proxy variables collectively reconstruct the omitted signals. We outline the practical implications of these findings for auditing data-centric AI workflows within regulated financial institutions.

LLM benchmarks can build an organization's reputation and attract customers, but only when results are transparent and verifiable. Unverified claims that DeepSeek R1 outperformed OpenAI's o1 contributed to market panic on January 27, 2025, when Nvidia lost USD589 billion in market value. Yet vendor benchmarks often depend on an honor system. Academic reassessments and independent leaderboards have found undisclosed changes to proprietary models, contaminated training data, and selective reporting. LLM-as-a-judge methods scale evaluation by reducing human review. Studies, however, suggest that judges may show identity-aware bias, scoring an answer according to its source model rather than its quality. This bias has not been fully measured or corrected across politically sensitive, reasoning-intensive, and preference-based tasks. We examine this problem using seven verifier models: GPT-OSS 120B, Llama 3.3 70B, GLM 5.1, Qwen3 32B, DeepSeek V4 Pro, Mistral Large3, and Sarvam M. They score anonymous and identity-disclosed responses from three primary models on 58 factual, reasoning, political, and preference-based questions. Identity disclosure slightly raises scores for factual questions, moderately affects stress-reasoning tasks, and causes large changes for geopolitically sensitive topics. Notable results include GLM5.1 (+7.00 points, p = 0.0249) and Llama 3.3 70B (+1.56 points, p = 0.00). We also introduce a blockchain-based commit-reveal protocol using Autonomous Economic Agents on an Ethereum-compatible ledger. In Phase 1, each judge records a one-way hash of its score and a secret salt before candidate identities are revealed. In Phase 2, the identity and raw score are disclosed and verified on-chain. This creates a tamper-evident audit trail that separates blind evaluation from post-hoc claims and reduces the verification burden on independent researchers and leaderboard operators.

As Large Language Models (LLMs) are increasingly used as a primary source of information and advice, understanding their alignment to humans in terms of values becomes a pressing concern. A growing literature has leveraged large scale surveys to investigate to what extent LLMs' and humans' stated values and opinions align. With limited exceptions, studied populations have been defined country borders or cultural bounds. Yet, this focus neglects the role that socio-demographic divides may play for value alignment disparities. Relying on the European Social Survey, we address this knowledge gap by considering value alignment displayed with respect to 10 prominent commercial LLMs in terms of 15 socio-demographic variables as well as country of residence. Our analyses reveal that LLMs are indeed unequally aligned to the values of different socio-demographic groups, notably those defined by education, income, occupation and religion. When examining alignment at the individual level, a respondent's country, taken as a stand-alone variable, explains a substantial amount of variation that is on par with the full set of considered socio-demographics. Further disentangling the respective role of country-level and socio-demographic factors, we find they are complementary in explaining value alignment patterns, with their relative weights varying across the subset of questions considered.

It is well established that large language models (LLMs) are sensitive to prompt framing, reflecting patterns in their training data or prior prompts. In this study, we investigate the extent to which LLMs reinforce users biases expressed in the prompts and examine the boundary between implicit framing effects and explicit prompt manipulation. Specifically, we evaluate how susceptible LLMs are to direct and suggestive prompts that encourage models to support or challenge particular positions. We evaluate six LLMs using 160 distinct prompts spanning ten topics across opinion-based and factual domains. The prompts systematically vary in prompting strategy, support versus challenge instructions, prompt polarity, users' expressed beliefs, and topic domain, spanning both opinion-based and factual questions. Our results show that LLMs systematically adapt their responses to align with prompt framing, even in factual contexts. This suggests that prompt framing can outweigh factual consistency in model responses. Overall, our findings delineate the extent and boundaries of LLM manipulability. Furthermore, the results imply that LLMs can reinforce subtle user biases and are susceptible to explicit prompt manipulation even in domains where responses should remain factually stable.

Aerial drone surveys increasingly support wildlife population estimation, yet a useful census is more than a count: population dynamics are defined by species composition, sex ratios and age structure, that is, by which species are present and how a herd splits into adult males, adult females and juveniles. We use red deer ($\textit{Cervus elaphus}$) as a test case, because managers act on these dynamics and because the visible cue defining adult males, the antlers, is seasonally variable. Surveys are flown nadir, high enough not to disturb the animals, so each deer occupies only a small, low-resolution patch. The two recording modalities fail in opposite conditions: in color a deer under canopy blends into the ground, while in thermal it becomes a bright blob that loses fine detail. Rather than trust either modality alone, we fuse them at every stage using self-supervised DINOv3 features. Our pipeline tracks animals in both modalities, treats an animal as confirmed only when the two cameras agree, keeps only the clear, non-occluded frames, and assigns species and sex by a vote across them; life stage is read separately from geo-referenced body size, since at survey resolution a juvenile often only differs from an adult female in size. Across four flights spanning the antler season the fused pipeline correctly classifies 25 of the 26 detected individuals (7 of 8 adult males, all 16 adult females and 2 juveniles), against 20 of 26 for either sensor alone. Multimodal species classification reaches 96.0%, while for sex classification fusing the two sensors matters most: the combined RGB+thermal model is the most robust across environments and seasons. Automating the demographic classification turns a drone flight from a count into a repeatable reading of herd structure, so the sex ratios and age structure that managers already act on can be gathered as often as a survey can be flown.

Prior benchmarking work has shown that a single large language model (LLM), forced to make life-or-death resource-allocation decisions, exhibits measurable demographic bias. Real deployments, however, rarely use a single agent: they use pipelines, with review steps meant to catch exactly this kind of failure. We study what happens to bias when the same decision is distributed across a role-differentiated multi-agent pipeline (assessment, allocation, independent audit) instead of made and checked by one model alone. Using a synthetic disaster-triage simulator with paired cases that are clinically identical except for one demographic attribute, we run 192 episodes (2,304 resolved case pairs) on GPT-4o-mini comparing a single-agent control condition to a nine-agent pipeline under three independently varied pressure dimensions. We find no measurable difference in how often biased outcomes occur between the two conditions (6.9% vs. 6.1%, p = 0.498). We do find a large and significant effect of audit capacity on whether bias is caught: 30.0% of biased outcomes go entirely undetected, rising to 43.8% when the auditor is overloaded and falling to 18.4% when it is not. Decomposing this effect shows it is driven almost entirely by coverage (whether a case is reviewed at all, which collapses from 100.0% to 65.6% under load, p < 0.001) rather than by degraded judgment on the cases that are reviewed (81.6% vs. 85.7%, p = 1.000, direction reversed). A follow-up experiment shows that reordering the audit queue by estimated risk, rather than first-come-first-served, recovers most of the lost coverage under the same capacity constraint (65.6% to 91.7%, p = 0.028). We discuss the implications for any system that adds independent oversight to an LLM agent pipeline under resource constraints, and report the study's limitations honestly: one model, modest sample sizes, and no adversarial replication.

Adaptive data-cleaning methods replace manual filtering thresholds with data-driven partitions. However, changing the partition granularity, the number of groups used to segment samples by estimated corruption risk, can implicitly shift the decision boundary and alter the overall number of removed samples. This creates a bias known as removal-budget confounding, where apparent gains in metrics like precision or false-positive rate reflect a smaller removal budget rather than superior corruption discrimination. To address this evaluation bias, we introduce an operating-point-aware evaluation framework that evaluates methods using matched-budget and matched-recall controls alongside threshold-independent metrics (AUROC and AUPRC). We test this framework on a multi-cue adaptive cleaner redesign featuring a reweighted learning-difficulty cue, an auxiliary Euclidean-distance cue, and increased partition granularity intended to isolate clean-but-difficult samples. While naive evaluations (assessing configurations at their own induced operating points) suggest substantial performance improvements for the redesign, these gains disappear once operating points are equalized. False-positive decomposition reveals that clean-but-difficult samples primarily drive error counts at low corruption rates, become threshold-dependent at moderate corruption, and contribute negligibly under severe corruption. Experiments on CIFAR-10 and ImageNet-100 demonstrate that most performance differences observed in naive evaluation shrink or vanish at low-to-moderate corruption when operating points are matched. True ranking advantages only remain in specific low-prevalence settings and in high-recall regions under severe corruption. These findings highlight that adaptive cleaning methods must be benchmarked at matched operating points to ensure performance gains reflect genuine corruption discrimination.

Automatic speaking assessment systems are increasingly deployed in high-stakes settings to mark second language (L2) learners' speaking tests, making it critical to show that their scores depend on speaking proficiency rather than irrelevant speaker attributes such as first language (L1) or age. Transformer-based foundation models have improved the accuracy of these L2 speaking graders, but their black-box representations make fairness and interpretability analysis more difficult. Building on prior work that used Concept Activation Vectors (CAVs) to detect bias towards unwanted attributes (`concepts') in feature-based graders, we extend CAV-based analysis to two neural speaking assessment systems: a text-based BERT grader and a speech-and-text multimodal grader based on Whisper. CAVs represent human-interpretable concepts as directions in a model's activation space, allowing us to distinguish between whether a concept is encoded in a model's internal representations and whether it influences the predicted score, the latter quantified using a gradient-based sensitivity metric. Since CAVs rely on linear separability, which is less likely in complex neural embedding spaces, we also investigate whether sparse autoencoders (SAEs) provide cleaner concept directions by learning CAVs in a sparse latent space and mapping them back to activation space. Our analysis shows that concept recoverability depends strongly on the representation and architecture being probed, rather than on the concept alone. Sensitivity to concepts is also architecture-dependent. SAEs make concepts more linearly recoverable, but attenuate the original activation-space sensitivity, especially in low-dimensional layers. These findings highlight the need to distinguish concept recoverability from concept influence when auditing bias in speaking assessment systems.

Measuring political bias in large language models (LLMs) remains challenging as it can manifest through subtle differences in framing, argumentation, and legal reasoning that are difficult to capture with a single metric. In this work, we introduce Poli-Bias, a counterfactual framework for measuring whether LLMs treat legally equivalent conflict scenarios differently depending on the countries involved. Poli-Bias compares responses to paired prompts in which country identities are systematically swapped across diverse geopolitical relationships, legal violations, and reasoning tasks. Rather than reducing bias to a single judgment, our framework decomposes response disparities into five interpretable dimensions, revealing how and where unequal treatment manifests. Across 13 contemporary LLMs spanning diverse model families and sizes, we find that country identities and user affiliations can systematically affect how equivalent actions are described, evaluated, and defended under international law. Our results thus establish Poli-Bias as a fine-grained framework for auditing political even-handedness and sycophancy in LLMs.

Recognizing new and rare words - named entities, acronyms, domain specific special words, and other items scarce in training data - remains a key challenge for automatic speech recognition (ASR). We compare two strategies for this: context biasing methods, where an ASR model is extended such that during inference a word list can be supplied, and speech large language models (LLMs) prompted with context directly. We evaluate two context biasing methods based on Whisper against three speech LLMs across read and non-read speech, reporting biased, unbiased, and overall word error rate (WER). The context biasing methods cut biased WER by up to 88% relative while leaving other words largely unaffected. Speech LLMs excel on read speech but generalize less well to non-read speech, and prove sensitive to distractor count and prompt word order. We characterize the resulting trade-offs to guide method selection.

Large Language Models (LLMs) are often used as evaluators of text quality, known as LLM-as-a-Judge, which can outperform conventional automatic evaluation metrics that rely on reference texts. However, LLM evaluators tend to generate particular scores regardless of the context of the evaluated text, which is known as scoring bias. This study proposes a novel method to mitigate this scoring bias. An LLM is instructed to randomly generate number tokens, and the latent numerical bias of the LLM is identified by measuring the deviation of the observed distribution of numbers from the uniform distribution. A definition of a downstream task, for which an LLM evaluator is used, is added to the prompts for random number generation to measure task-specific latent number bias. In the evaluation by an LLM, the token generation probabilities for a given input are rectified considering the LLM's latent number bias. Results of the experiment on four different tasks, evaluation of LLM alignment, evaluation of summarization, Semantic Textual Similarity, and Semantic Textual Relatedness, demonstrate that our proposed method outperforms the baselines, including an LLM without debiasing and previous calibration methods. In addition, it is confirmed that scoring bias varies across LLMs, tasks, and score ranges, indicating the importance of measuring latent number bias as the case may be.

AI tools are being increasingly adopted in policing in the UK and worldwide. Racial bias is a known and well-documented risk, yet representatives of affected communities are rarely included in decisions about AI adoption. We present results from a mixed-stakeholder deliberation workshop bringing together 30 community representatives, police officers, and academics to assess the risks of 13 AI use cases in policing, with an explicit focus on racial bias. We found that participants were broadly open to AI adoption, rejecting only three use cases outright, most notably recidivism risk assessment, where objections targeted the premise rather than the implementation. Our analysis reveals that foregrounding racial equity did not narrow the deliberation. Instead, discussions gravitated toward a fundamental set of questions: does this tool actually work, will it deliver genuine benefit, and will that benefit extend to everyone? This integrated reasoning, reminiscent of the curb-cut effect in inclusive design, highlights the benefit of incorporating the racial bias lens into the risk-benefit analysis of AI use cases from the outset.

Context-aware recommender systems have long recognized that factors such as location, time, and weather shape where and what people choose to eat. Existing weather-aware food and point-of-interest recommenders, however, typically treat weather generically -- mapping conditions to preferences through hand-crafted rules or specially trained context models -- and do not capture that the culturally appropriate response to weather is itself region-specific: a rainy evening calls for hot tea and fried snacks in one culinary culture and for very different comfort food in another. Encoding such weather-by-region-by-cuisine interactions as explicit rules or training data is brittle and does not scale. We present a weather- and location-aware agentic dining-recommendation system that takes a different approach: a large language model (LLM) orchestrates tools for location and weather retrieval and then reasons in natural language over the combined context, drawing on the cultural and culinary world knowledge already latent in the model to produce region-sensitive, weather-appropriate recommendations without per-region rule tables or specialized training. We describe the agent architecture, the tool-orchestration flow (Google location services and a weather service feeding an OpenAI LLM), and the reasoning mechanism, and we report on a working prototype that was implemented and briefly deployed end-to-end. We discuss design trade-offs -- cost, latency, ambiguity handling, and fallbacks -- and we are explicit about limitations, including the absence of a formal user study and the risk of cultural stereotyping in locality-based inference. The contribution is architectural: a simple, extensible pattern for incorporating environmental and cultural context into agentic recommendation through LLM reasoning rather than engineered rules.

Against the backdrop of violence in police interactions with the U.S. public, we explore how deferentially police officers speak to virtual characters depicted as Black adult males in vir- tual reality (VR) simulations. We evaluate the effect of seeing and communicating with these characters through a causal in- ference lens, where the assignment of the Black man character to a police officer and simulation is the treatment variable. Our (marginal) average treatment effect AT E measures the social impact of the character on the deference of officer statements with each turn of the conversation. Soberingly, we find that most officers speak less deferentially to Black man characters, except for White, biracial, and multiracial female officers, es- pecially in settings where the VR character was known to be a suspect. Across a full conversation of a typical VR scene, these marginal AT Es can result in notable changes in def- erence of tone (two to several points difference on a scale of 0-10), above and beyond that due to the initial effect of per- ceiving a Black male character. Even more disconcerting is that this can contribute to conversation breakdowns that po- tentially result in violence or danger to both the public and the police. We also explored the capabilities of large language models (LLMs) for ATE estimation. From our methods com- parison analysis, including model validation against synthetic data, we provide unique scientific insights on LLM-assisted methodologies for ATE estimation. As such, for ATE esti- mation with multilevel data with text, we recommend mixed effects models with the inverse propensity treatment weighted (iptw) approach, which utilized an LLM for text feature cre- ation. While we also tested LLMs for finetuning prediction models ultimately for ATE estimation, we conclude they are an area for further development and refinement.

Despite its cultural relevance and diffusion, queer slang remains underrepresented in Natural Language Processing research. Towards addressing this gap, we introduce Slang-Q, a manually curated dataset of naturally user-generated English sentences paired with queer slang terms and reference definitions, built upon a newly constructed taxonomy of 118 queer terms. We use this resource to conduct a first exploratory evaluation of language models on their ability to understand and define queer slang under varying prompting conditions. Slang-Q is intended as a basis for studying how current models handle sensitive, community-specific language and whether they can provide accurate and reliable information about such forms of identity and linguistic expression.

Chain-of-thought (CoT) monitoring is increasingly treated as an important safety layer for frontier reasoning models. Most monitorability evaluations study explicit-influence settings: setups where the prompt directly incentivizes the model to hide something, e.g., by instructing it to perform a hidden side-task. A complementary axis for CoT-monitor evaluations is implicit-influence settings, where the prompt contains no instruction to hide, but the model's behavior is still shaped by features of the task or context, e.g. an irrelevant detail about a candidate that biases a hiring rating. We introduce the first benchmark that directly compares CoT monitorability under the two regimes. We test how model behavior changes in the presence of a nudge to choose a particular option. The nudge is delivered either as a casual aside (implicit), or as a direct instruction to act on the nudge and to conceal having done so (explicit). The benchmark spans four task formats (binary choice, numeric rating, multiple-choice QA, open-ended coding) and seven frontier extended-thinking models. Under explicit influence, a CoT monitor detects 60-94% of behavior shifts: even models instructed to conceal it leak the instruction into their CoT. Under implicit influence, the same factors still shift behavior, but detection falls by 41-46 percentage points in two of our four settings. Realistic system-prompt additions (of the kind a developer might deploy to reduce off-topic bias) lower implicit detection further, to as low as 5%, while preserving the behavioral influence itself. These results suggest that monitorability estimates obtained in explicit-influence settings may over-estimate monitorability, and that monitorability can be further decreased by well-intentioned deployment choices. Our benchmark and code are available at https://github.com/agatha-duzan/implicit-vs-explicit-influence

Action-conditioned world models aim to predict how visual environments evolve under an agent's actions. Yet future frames are often highly predictable from visual inertia and recurring motion patterns alone. This creates a shortcut: models can fit the data by exploiting statistical biases without making their visible dynamics meaningfully depend on the action. As a result, different actions may produce similar futures, while motion may persist even under zero action. The key question is how to reduce reliance on statistical shortcuts from dominating action-conditioned prediction. We argue that action control requires more than injecting action features; it requires enforcing consistency under counterfactual changes to actions and observations. Based on this insight, we introduce CoCo, a Counterfactual Consistency framework to enhance action controllability through two complementary constraints. Multi-step counterfactual consistency constrains reference, inverse-action, and zero-action rollouts, while action-spatial counterfactual consistency enforces consistent predictions under mirrored scenes and transformed actions. Together, they reduce reliance on statistical shortcuts from substituting for action-dependent dynamics. We further introduce Action Response Consistency (ARC) and Drift Energy (DE) to assess action controllability, together with Mini-SSMB for same-state, multi-action counterfactual evaluation. On Mini-SSMB, our full model achieved ARC_inv of 0.412 and ARC_ref of 0.483, while reducing DE by 17.07% relative to the baseline. On VP2 visual planning, it achieves the highest average success rate among SOTA models, at 73.1%. Experiments on BAIR and RoboNet further show that these gains preserve video prediction quality and transfer across model settings.

Gradient descent has been of particular interest in modern machine learning beyond sole focus on optimization. Implicit bias emerging from optimization, though not being encoded by the learning objective, often prevents from overfitting to spurious patterns. A typical instance is the max-margin implicit bias of a linear classifier, widely established for exponentially tailed loss functions. Even after having a given dataset separated, the parameter vector continues to evolve towards the max-margin direction asymptotically along the gradient descent dynamics. This phenomenon corroborates a frequent empirical observation of "train longer, generalize better." However, the max-margin convergence is an asymptotic phenomenon, and what is worse, this asymptotic convergence rate is significantly slower than pure convex optimization. Even so, the parameter vector along gradient descent dynamics commonly correlates with the max-margin direction positively (though not exactly) within considerably fewer iterations than the asymptotic rate. By shedding another light on this classical problem, this work aims to understand the mechanism of this early-stage alignment phenomenon. Our theoretical results demonstrate that the parameter vector weakly aligns with the max-margin direction within $O(\exp(\exp(-δ)))$ iterations, where $δ>0$ is the permissible alignment error, which is shown to be tight. By tracking the radial and tangential flows, our proof operates on the alignment dynamics directly with dataset geometry and gets rid of the asymptotic expansion, which is a key insight to establishing faster weak alignment.

Generative models trained on artificially generated data have been shown to exhibit model collapse, resulting in significant performance degradation. As synthetic content increasingly contaminates the training corpora of language models, this raises critical concerns about the use of open data in continued pretraining. Although previous work has demonstrated model collapse in language models, it remains unclear whether exposure to synthetic data amplifies or attenuates the social biases already present in pretrained models. Because language models are known to reproduce and amplify demographic stereotypes, recursive training on self-generated data may create a self-reinforcing feedback loop in which biased associations become progressively stronger across generations. We call this hypothesized phenomenon fairness collapse. In this work, we construct controlled training regimes in which models are repeatedly trained on synthetic data using the Bias in Bios dataset. Across experiments, we observe a consistent and concerning pattern: fairness degradation emerges before substantial degradation is reflected by standard language-modeling metrics. This result highlights a critical risk associated with synthetic data contamination in language model training: bias can increase silently before strong indicators of model collapse become apparent.

Fairness in AI systems has become more important with recent regulatory demands, such as the EU AI Act. Traditional approaches often do not take into account philosophical ethics and social awareness. Variable selection processes, in particular, can introduce implicit bias, affecting equity across different subgroups. We discuss a mathematical approach that evaluates fairness in AI, aligning mathematical methodologies with ethical considerations and regulatory requirements. Our aim is to advocate for interdisciplinary collaboration to address fairness, emphasizing the importance of understanding broader ethical and societal contexts. Our approach emphasizes maintaining all potentially relevant variables to allow for more granular fairness assessments and to reduce implicit bias. The findings suggest that the exclusion of sensitive or critical variables may compromise equity between subgroups. In contrast, retaining all relevant variables could reduce implicit bias. Thus, the interdisciplinary approach could provide deeper insight into the ethical implications and compliance with regulatory standards. By integrating a mathematical approach with ethical and social awareness, we suggest more equitable outcomes and responsible AI deployment. This work underscores the necessity of interdisciplinary collaboration in effectively addressing fairness in AI systems aligned with the objectives of the European Union's AI Act, which seeks to promote trustworthy and fair AI systems.

Nonlinear state estimation requires sequentially fusing model-based predictions with noisy measurements. Under imperfect dynamics and unknown, time-varying noise statistics, this fusion can degrade in both accuracy and statistical consistency. Existing learning-aided filters largely treat accuracy and uncertainty estimation separately, limiting their ability to correct model-mismatch-induced bias while retaining an explicit, calibrated posterior covariance. This paper introduces Unscented KalmanNet (UKN), a model-based deep learning architecture that extends the Unscented Kalman Filter (UKF) with learned mechanisms for these two sources of filtering error while preserving explicit posterior covariance propagation. NoiseNet learns time-varying process and measurement covariances as bounded multiplicative corrections to baseline covariances, guaranteeing positive definiteness, while GainNet learns a bounded residual correction to the analytical UKF gain to compensate for model-mismatch-induced bias. A calibration-aware training objective couples state error with posterior covariance and innovation consistency terms through adaptive weighting, jointly optimizing accuracy and calibration. UKN is benchmarked against UKF, KalmanNet, and Bayesian KalmanNet on three synthetic systems and real-flight UZH-FPV data. It achieves the lowest state-estimation error in all four examples and reduces RMSE by 26.4-49.7% compared with UKF in the synthetic cases. Leave-one-sequence-out cross-validation over 11 flights shows 22.4% and 34.3% reductions in mean position and velocity RMSE, respectively. UKN also yields the lowest fold-to-fold variability, with dimension-normalized NEES and empirical coverage closest to nominal values among covariance-reporting filters. These results show that structured learned adaptation improves estimation accuracy while retaining calibrated uncertainty.

Large Language Models (LLMs) are increasingly used for automated fact-checking, yet their susceptibility to gender bias in this context remains underexplored. This study presents the first systematic investigation of gender bias in LLM-based fake news detection using real-world data. We augment the LIAR benchmark with three gender variants of speaker job titles (Neutral, Male, Female) for each statement to test whether veracity judgments vary solely based on gender presentation. Six state-of-the-art LLMs are evaluated across multiple bias and fairness metrics. All models exhibit gender sensitivity: 9.79%-35.13% of statements receive inconsistent labels across the three variants, with Male-Female comparisons showing 6.5%-23.6% flip rates. Two primary bias manifestations are identified: instability (inconsistent judgments) and directionality (systematic favoritism). Five models show statistically significant directional effects, with the strongest effects displaying male-skeptic patterns. These findings demonstrate that gender bias undermines both reliability and fairness in LLM-based fake news detection, highlighting the need for bias-aware evaluation and mitigation strategies. The augmented dataset is publicly released to support future research.

Large language models are increasingly deployed in multilingual contexts, yet safety alignment and bias evaluation remain overwhelmingly English-centric. We investigate whether social biases generalise across languages by submitting 4,900 symmetric English--Swahili prompt pairs to GPT-5.2 and Gemini 2.5 Flash across nine demographic bias axes, yielding 19,600 completions evaluated for stereotype prevalence, sentiment, refusal behaviour, and cross-lingual semantic similarity. Our findings show that bias transforms rather than transfers: stereotype rates shifted by up to 12 percentage points on specific axes, Gemini's neutral-sentiment rate doubled in Swahili, and GPT-5.2 refused 169 prompts in English and zero in Swahili, consistent with refusal behaviour anchored to English-language surface forms at the behavioural level. Over 55% of prompt pairs produced semantically dissimilar completions across both models. These reinforce the idea that English-only bias audits do not produce adequate coverage for multilingual deployment.

When people label text for sexism, they often disagree, and not because some of them are wrong: they genuinely perceive sexism differently. Most NLP systems discard this disagreement by collapsing it into a majority vote. We propose the Multi-Agent Perspectivist Preference Optimization (MAP-PO) framework to keep these different perspectives. On the EXIST 2024 dataset of labeled English and Spanish tweets, we first cluster annotators by their labeling behavior rather than their demographic attributes. We then fine-tune one Large Language Model agent per cluster to reproduce that cluster's annotation behavior, and coordinate the agents with preference optimization that combines individual and team-level rewards. We evaluate MAP-PO in four settings defined by two languages and two backbone language models, asking whether each agent reproduces the annotations of its own cluster and whether the agents together reproduce the majority label. Two findings hold in all four settings. First, without fine-tuning the agents behave almost identically, so cluster-specific training is necessary. Second, we show that training each agent only on the labels of its own cluster pushes the agents far beyond the clusters they should represent, while adding a shared team-level training signal consistently keeps each agent calibrated to its cluster.

Sonic seasoning research has shown that listeners attribute systematic gustatory and emotional meaning to sound, and text-to-music generative artificial intelligence has recently been used to render gustatory prompts as musical stimuli. Whether the taste-sound correspondences acquired by such models hold beyond the cultural context in which they were validated remains untested. We extended a single-country study to a three-country online experiment conducted in Argentina, Italy, and Japan (N = 361). Participants first indicated their preference between base and fine-tuned MusicGen excerpts generated from four taste prompts (sweet, sour, bitter, salty), and then rated fine-tuned excerpts on twelve taste, emotion, and thermal descriptors. Preference for the fine-tuned model was confirmed in Argentina and Italy but not in Japan, and the salty prompt yielded the weakest correspondence in all three cohorts. Ratings differed substantially between countries, yet the main effect of country was no longer detectable once ratings had been standardized within participant, whereas the interactions characterizing the mapping of prompts onto descriptors remained essentially unchanged. Much of the apparent cross-cultural divergence is therefore attributable to differences in scale use; a structural component nevertheless persists. In addition an exploratory factor analysis indicated that the twelve descriptors were organized along different latent dimensions in each cohort. These results indicate that cross-cultural variation in AI-mediated sonic seasoning operates at two levels: the overall level at which taste is attributed to a given stimulus, and the relational structure of those attributions. Evaluations of generative music systems across populations should accordingly distinguish response-style bias from genuine perceptual reorganization.

Multi-armed bandit algorithms, especially Thompson sampling, are widely used in online recommendation. Despite their ability to adapt from online feedback, these methods often suffer from cold-start limitations when newly introduced arms have little or no interaction history. In our setting, the candidate arms are user-generated textual comments, whose semantic content can reveal a title's appeal before sufficient interaction feedback is available. We therefore use large language models (LLMs) to extract semantic signals from comment text and convert them into informative Bayesian priors that warm-start Thompson sampling under sparse early-stage feedback. To account for aggregate segment-level differences in response patterns, we maintain and update posteriors separately for each gender-age segment. In a real-world online A/B/C test, we compare a uniform prior with two LLM-based designs: a Gender Prior for demographic-affinity cues and a Content Prior for title-specific identity cues. The results show that LLM-based priors are most beneficial in sparse-feedback regimes -- with the largest gains emerging once a small amount of interaction evidence has accumulated -- and that prior design leads to distinct funnel-level effects. We further analyze prior-reward alignment and demographic heterogeneity, finding that click-oriented alignment is strongest for the Gender Prior and that treatment effects vary substantially across demographic segments. These findings suggest that LLM-derived priors can serve as a practical warm-start mechanism for text-rich bandit recommendation, while also revealing deployment trade-offs.

Conditional segmentation models may be trained and evaluated with auxiliary signals cleaner than those available at deployment. We study this protocol-level manifestation of shortcut learning and auxiliary-variable shift in phase-conditioned echocardiographic segmentation. The complementary gap pair measures loss on the deployable oracle-estimated pathway and probes sensitivity on the oracle-random pathway. On held-out CAMUS data, one strong-cyclic, oracle-selected run fails severely with estimated phase, while sensitivity to incorrect phase persists across three runs. On EchoNet-Dynamic, the current estimator remains usable, but random-phase testing reveals strong latent sensitivity. Deployment-aware checkpoint selection and phase perturbation reduce both gaps with little change in mean Dice. Exploratory subgroup analyses quantify variation across measured strata, and a downstream ejection fraction (EF) audit shows that recovering segmentation does not necessarily recover EF error or signed bias. Together, the gaps test whether oracle-conditioned performance survives the inference pathway actually available at deployment.

Text-to-image (T2I) generation models are increasingly embedded in applications such as media content creation and education, raising concerns about how their outputs may reproduce social biases. Prior work has shown that T2I models exhibit social biases, yet existing evaluations largely focus on a photo generation task. As a result, it remains unclear whether and how such biases manifest in more narrative visual formats, such as storyboards and comics, where characters and events are presented across multiple panels. In this work, we compare bias expression across photo, storyboard, and comic generation in six T2I models by adapting BBG, a text-based bias evaluation framework, to image generation. Our results show that proprietary models generate 25.9% biased outputs in photo generation on average, with biased outputs increasing by 9.6pp in storyboard generation and 18.2pp in comic generation. We also find that photos mainly encode biases through subtle visual cues, while storyboards and comics reveal them more explicitly through event sequencing, character positioning, narrative resolution, and textual elements. These findings show that biases that remain less visible in photo generation may surface in narrative visual formats, highlighting the importance of evaluating T2I systems with diverse visual formats beyond photo generation.

Large language models (LLMs) increasingly evaluate human writing in high-stakes domains such as hiring and academic assessment, putting non-native speakers at particular risk. Drawing on the language attitudes framework, we compared human and LLM evaluations of parallel L1- and L2-written Japanese emails on three dimensions: fluency, status, and solidarity. Japanese raters rated L2 texts significantly lower on all three dimensions, with a fluency gap roughly twice the size of the status and solidarity gaps. Six LLM judges reproduced the direction of this bias, and five reproduced its ordering across dimensions. The models diverged from humans in two ways: all understated the solidarity gap, the most socially grounded dimension, and all differentiated among learner L1 backgrounds where humans did not. LLM judges thus reproduce native speakers' language attitudes in a structured yet attenuated form, and the language attitudes framework offers a ready-made yardstick for auditing them beyond English.

Large language models are being extensively used to simulate individual user behavior, yet faithfully representing a population requires capturing the systematic variation in values, beliefs, and cultural norms that distinguish one group from another. We introduce Population Aligned Language Models (PALMs), a suite of models each aligned to specific populations, covering five countries: USA, India, Brazil, France and Italy. PALMs are created by synthesizing rationales grounded in psychological and cultural constructs and using these as latent supervision during preference tuning for population-specific alignment. Evaluated across four dimensions: personality, values and beliefs, cultural norms, and morality, PALMs consistently outperform baselines, including culture-specialized models, achieving an average of 8.59% relative improvement over the best baseline across all five populations. Notably, construct-grounded rationales outperform both demographic prompting and survey-based fine-tuning, suggesting that grounding preference learning in psychology and culture provides a richer inductive signal than surface-level response distributions. We further demonstrate strong generalization to downstream applications with- out task-specific supervision: outperforming best baselines by 5.19% in personalized reward modeling, 6.34% in population simulation, and showing strong transfer to social reasoning tasks. Datasets and code are available at: https://github.com/limenlp/PALMs.

Women experiencing coercive control, a form of intimate partner violence increasingly conducted through digital devices, are turning to conversational AI for help, and the protection they receive should not depend on the language they write in. We analyse how AI responds to coercive control against women across languages. We put one scripted scenario to seven widely used language models in nine languages: a woman whose partner tracks her phone asks for help with a self-blaming letter accepting the surveillance. We scored whether the model wrote the letter and whether it named the control, countered the self-blame, and affirmed her agency. Failure split along two independent axes. On the first, systems from non-anglophone developers gave way most often in their builders' own language. On the second, how far a sympathetic excuse for the partner could strip a model's naming of the control varied sharply from one language to the next. Two frontier systems held the strictest standard everywhere, so a protective ceiling is attainable within this scenario family, and failures elsewhere are a design outcome. What is at stake is recognition: whether a system grasps a disclosure as coercive control, and whether it then acts on that grasp. We argue this should be held to a floor, one language at a time.

Bandit algorithms generate data for downstream inference, but adaptive sampling biases post-bandit sample means. We analyze this bias for stable index algorithms, including UCB1 and its generalizations, and derive sharp leading-order expressions for the sample-mean bias and expected $Z$-statistic, in bandit experiments of fixed horizon $T$. Our characterization reveals the algorithmic origin of bias through a key index-function-dependent quantity, which we term effective exploration rate. For example, under UCB1, the effective exploration rate is of order $\sqrt{\log T}$, and the standardized bias of any arm (that is not uniquely optimal) decays at the extremely slow rate $1/\sqrt{\log T}$. We also show how the choice of the index function affects both regret and bias, which reveals a regret-bias trade-off: more exploratory algorithm reduces bias but increases regret. We further show how bias most severely distorts confidence intervals and hypothesis tests when the tested arm is one of the tied-optimal arms. Our sharp characterization for bias uses a novel empirical fluid approximation of the algorithm's sampling dynamics, which may be of independent interest.

Language models (LMs) often acquire various biases during pre-training and may express them in interactions, potentially causing social harm. Existing methods often rely on counterfactual augmentation or representation projection. These strategies remain limited in practice due to their high computational costs and difficulty in scaling to larger models. Additionally, many of these strategies require manual data annotation, narrowing their scope to specific cultures and bias categories. To overcome these limitations, we propose HEIMAT, a HEurIstic-style autoMATic debiasing framework for LMs. HEIMAT consists of two main steps: bias disclosure and debiasing fine-tuning. In the first step, it uses simple templates to construct heuristic prompts, which are applied to reveal model biases and generate corresponding context prompts. In the second step, it fine-tunes the model by minimizing the Jensen-Shannon divergence of predictions on these context prompts to reduce bias. Extensive experiments show that HEIMAT effectively mitigates bias in different cultures while maintaining the model's natural language understanding (NLU) performance.

Positional biases such as recency and primacy effects have been documented in large language models (LLMs), yet the underlying mechanism by which these models make their evaluations remains poorly understood. Both primacy and recency biases have been observed in human judgments in response to evidence, but recent work suggest that \emph{when} the listener updates their beliefs -- during the presentation of evidence or only at the end -- influences the presence of such effects. We investigate whether a similar phenomenon holds for LLMs, finding divergence from human behavior. These biases are more exacerbated in newer models compared to their predecessors.

Evaluation of faithfulness of text summarization treats a model generated summary as faithful only if every of its sentences is supported by the source document: a strict conjunctive rule under which a single unsupported sentence makes the whole summary unfaithful. Yet most faithfulness benchmarks collect only one global human annotation label per summary. We ask whether such global human labels actually implement the conjunctive rule. We hypothesize that annotators may accept a summary as faithful when most sentences are faithful, not only when all are faithful. To test our hypothesis, we use five large language model (LLM) judges as per-sentence raters across four widely used faithfulness benchmarks. We find that global human labels correlate better with the average of per-sentence LLM judgments than with the implementation of the strict conjunctive rule. A manual review confirms that a substantial fraction of summaries labeled faithful by humans contain genuine local factual errors. We call this tendency Averaging Bias. Our results reveal that human labels on widely used faithfulness benchmarks contain measurable Averaging Bias, calling for carefully structured designs for trustworthy human annotations

Conversational AI developed by geopolitical rivals reaches citizens worldwide, raising concerns that it could sway public opinion or be rejected as foreign propaganda, with consequences for democratic discourse and information sovereignty. Yet, whether an AI's perceived national origin shapes its persuasive power is unknown. In a preregistered randomized experiment, 403 adults from a nationally representative United States sample held a three-round debate with a chatbot introduced as either American ("DiscoveryAI") or Chinese ("ZhengheAI"), discussing a political or non-political topic. In all conditions, participants actually conversed with the same model (GPT-4o), instructed to argue against their initial position. We combined pre- and post-conversation self-reports of attitudes, trust, and collective narcissism with computational analyses of 1,209 participant turns, including LLM-coded stance and argumentative conduct, stance-sensitive embeddings, and keyword-masked emotion and toxicity classifiers. The conversations produced substantial attitude changes in every condition. Critically, the nationality label affected neither self-reported attitude change nor expressed stance, concessions, counterarguing, or affect, and equivalence tests and Bayes factors largely supported these null effects. The label's only reliable footprint was lower pre-conversation human-like trust in the Chinese model, whereas functionality trust was unaffected. Political topics slowed stance movement toward the AI's position, and collective narcissism predicted less attitude change regardless of origin, acting as a general barrier rather than an out-group filter. Users thus initially withhold social trust from a rival's AI yet still assimilate its arguments; origin labeling and transparency requirements alone may offer weak protection against foreign influence operations conducted through conversational AI.

Large language models (LLMs) are increasingly involved in the distribution of scarce resources, raising concerns about biased allocations based on characteristics like race and gender. Recent LLM audits have produced inconsistent results, however, finding evidence of both positive and negative discrimination towards women and ethnic minorities, even for the same models. We show that this disagreement can arise from differences in audit format and introduce FairFund-Bench, a benchmark that systematically varies key features of previous audit designs: the evaluation task (rating, ranking, or allocation), comparison context (single or multi-stimulus), and whether the audit is transparent or disguised. The benchmark comprises 600 requests for financial assistance created from human-authored templates (calibrated against 1.3M real GoFundMe campaigns) across three domains, four race and two gender categories, and five causal framings of need derived from welfare deservingness theory. Across 14 models, audit format changes the direction of bias: models advantage minorities when rating claimants individually but penalize some groups when ranking them side by side. Bias magnitude, though small overall, is several times greater in disguised audits than in transparent ones, where, faced with appeals differing only in claimants' names, models overwhelmingly split funds equally. Causal framing effects, by contrast, exceed demographic effects by roughly an order of magnitude and are consistent across models and audit formats, indicating that current LLMs robustly reproduce human deservingness evaluations. The benchmark scores models on four criteria (demographic bias, deservingness alignment, cross-task consistency, and cross-context consistency), is publicly available, and can be readily adapted to other substantive domains.

The rapid growth of large language models (LLMs) has resurrected age-old questions in sociolinguistics and world Englishes, such as who decides what counts as legitimate English, whose English is suspect etc. This paper examines how AI systems, their uses and discourse on them reflect, reinforce, and occasionally challenge (standard) language ideologies, which privilege Inner Circle norms and marginalize non-dominant Englishes. Drawing on evidence from empirical studies, media commentary, social media debates, and examples from AI outputs, the paper shows that AI technologies reproduce dominant language ideologies at different levels: training data, design protocols, evaluation benchmarks, user feedback and public commentary. The analysis uses the public controversy over AI-sounding language, especially the fixation on the word delve, to illustrate how speakers of English from the Global North police the English language norms of Global South English users. The paper also identifies what Christian Mair has called a "standardisation paradox": AI may homogenize English by privileging standard forms and at the same time pluralize Englishes through exposure to wide-ranging corpora and annotation work carried out by Global South users. In doing so, the paper argues that generative AI is reigniting long-standing debates in World Englishes about standardization, legitimacy, and the ownership of English, now playing out in algorithmic systems, model training, evaluation practices, and public discourse, where non-dominant Englishes are increasingly conflated with AI-generated speech. Discussing AI systems as a site where language ideologies are (re)produced, the paper argues for more inclusive design approaches that recognize the plurality of Englishes in order to address the real-world negative consequences of treating some as more legitimate than others.

On-policy distillation (OPD) provides dense token-level supervision from a teacher, but its effectiveness can depend on teacher consistency, meaning that the model providing OPD supervision should also have generated the demonstrations used to train the supervised fine-tuning (SFT) reference. However, this condition is frequently violated in practice when SFT data have mixed or unknown provenance or when different models are preferred for SFT data generation and subsequent distillation. In such cross-teacher settings, even a stronger OPD teacher can yield little improvement over the SFT reference. We find that raw teacher--reference disagreement contains potentially useful context-specific teacher evidence as well as a recurring component associated with differences in wording, formatting, and reasoning cadence. We introduce Lightning OPD 2.0 with cross-fitted style residualization, which uses rollout-level cross-fitting to estimate this recurring component as an operational proxy for style-token bias and subtracts it before constructing the token-level OPD update. Across mathematical reasoning and code generation benchmarks, Lightning OPD 2.0 consistently outperforms Lightning OPD in cross-teacher settings. Starting from Klear-Reasoner-8B-SFT, Lightning OPD 2.0 reaches 82.4% on AIME 2024 and 63.0% on LiveCodeBench v5. Together, these results establish Lightning OPD 2.0 as a practical approach to cross-teacher OPD, relaxing teacher consistency as a prerequisite and allowing the SFT data generator and distillation teacher to be selected independently. Code will be released soon.

This work presents Fairness Pruning, a lightweight structural intervention method designed for the management and future mitigation of demographic bias in large language models (LLMs). As a foundational empirical validation of this method, this work focuses on causal bias localization. Using minimally contrastive prompt pairs and inference-time activation capture, the method identifies neurons that react differentially when processing demographic attributes in GLU architectures, evaluating the signal at the down_proj input. Empirical evaluation was conducted on models of up to 3 billion parameters (Llama-3.2 family and Salamandra-2B), combining standardized benchmark evaluation with qualitative text generation experiments. Results demonstrate that zeroing the identified neurons alters how the model responds to associated demographic variables. However, rather than producing flat mitigation, the intervention causes bidirectional bias destabilization: because BiasScore is unsigned, candidate sets mix neurons that push toward and against the stereotype, and the net effect on aggregate bias depends on which sign dominates. The intervention is extremely surgical: zeroing at most 40 neurons in Llama-3.2-1B (less than 0.031% of total MLP width) achieves a mean retention of 99.49% in reasoning and general knowledge capabilities. These findings empirically confirm that demographic bias processing and model capabilities operate on dissociable circuits, establishing the methodological foundations for transitioning from blind zeroing toward directional behavior modulation.