Social Bias in Language Models

Momentum

13 papers in the last four weeks, up 44% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 126

Jun 3, 2026cs.AI

BiasGRPO: Stabilizing Bias Mitigation in High-Variance Reward Landscapes via Group-Relative Policy Optimization

Mitigating social bias in Large Language Models (LLMs) presents a distinct alignment challenge: unlike verifiable tasks, bias lacks a single ground truth, creating a high-variance, subjective reward landscape. Previous preference-based fine-tuning methods have major trade-offs: Direct Preference Optimization (DPO) is limited by the lack of exploration inherent in offline training, while Proximal Policy Optimization (PPO) can lead to training instability due to potentially unreliable critic estimates. In this paper, we propose BiasGRPO, a framework using Group Relative Policy Optimization (GRPO) to stabilize alignment by normalizing rewards across a group of sampled completions. By substituting the value function with a group-relative baseline, our approach reduces instability while maintaining the exploration benefits of online training. We find that BiasGRPO outperforms DPO and PPO across multiple benchmarks, indicating its effectiveness. To adapt GRPO, we synthetically extend a dataset spanning multiple domains and contexts. We also create and release a custom bias reward model that effectively guides generation while being highly compute-efficient and avoiding knowledge degradation, providing a valuable resource that can be seamlessly integrated into multi-objective RLHF pipelines.

Saket Reddy, Ke Yang, ChengXiang Zhai

University of Illinois - Urbana-Champaign

Reward Modeling RL for Language Models LLM Alignment Social Bias in Language Models Group Relative Policy Optimization

Ask PDF

Jun 1, 2026cs.CL

Topics as Proxies for Sociodemographics: How Conversational Context Affects LLM Answers

When large language models (LLMs) are used in high-stakes scenarios, such as legal, medical and financial advice, even a single conversation history is enough to drive differences in outcomes between users. Prior work has demonstrated that this results in outcome disparities between sociodemographic groups, with some groups receiving more advantageous outcomes than others. In this work, we demonstrate that LLMs actually struggle to infer user sociodemographics from a single conversation history and that although there are disparities between sociodemographic groups, they are minimal in magnitude. To investigate what the main driver of these disparities is, we compare user sociodemographics to a range of (psycho)linguistic features of conversations, including conversation topic, emotions, and readability. We find that conversation topics are most predictive of LLM-generated advice within a conversational context, which, to some extent, function as proxies for sociodemographic groups and often affect advice in unpredictable ways. This is cause for concern and highlights the need for future research to better understand and, if needed, mitigate the effect of conversational context on LLM outputs in high-stakes scenarios.

Vera Neplenbroek, Gabriele Sarti, Arianna Bisazza +1

Institute for Logic, Language and Computation, University of Amsterdam · Khoury College of Computer Sciences, Northeastern University · Center for Language and Cognition, University of Groningen

Social Bias in Language Models Language Modeling Language Model Bias Evaluation Demographic Bias in Language Models

Ask PDF

Jun 1, 2026cs.CL

Identifying High-Confidence Social Biases in LLMs for Trustworthy Conversational Tutoring Agents

Conversational tutoring agents have been shown to improve learning engagement and student outcomes, and large language models (LLMs) are increasingly used in these systems to provide scalable, personalized feedback. However, LLMs may perpetuate or amplify stereotypical social biases, posing particular risks in educational settings. In this study, we evaluate LLMs in conversational tutoring scenarios to identify high-confidence social biases, instances where models are unable to identify biased judgments in tutoring conversations while maintaining strong confidence in their assessments, potentially affecting their reasoning and the feedback they provide to learners. We present a new dataset generation method that enables bias evaluation under naturalistic instructional conditions by regenerating student-AI tutor interactions and introducing turns with controlled bias derived from a benchmark dataset. Using this data, we assess multiple LLMs' ability to detect stereotypical biases and analyze the confidence and reasoning underlying their responses through computational and human evaluations. We find that bias detection is substantially more challenging in conversational tutoring contexts than in benchmark-based evaluations, and that state-of-the-art LLMs are overconfident in their incorrect assessments of stereotypical bias statements. Moreover, model confidence strongly influences reasoning and feedback, highlighting the risks of overconfident, biased behavior in LLM-based tutoring agents. We conclude by discussing implications, mitigation considerations, and directions for future research.

Aitor Arronte Alvarez, Naiyi Xie Fincham

University of Hawaii at Manoa, Honolulu HI 96822, USA

Intelligent Tutoring Systems Social Bias in Language Models Language Model Calibration Language Model Bias Evaluation

Ask PDF

May 28, 2026cs.CL

COFT: Counterfactual-Conformal Decoding for Fair Chain-of-Thought Reasoning in Large Language Models

Large language models (LLMs) can reveal and amplify societal biases during chain-of-thought (CoT) generation. We present COFT (Chain of Fair Thought), a training-free decoding method that applies token-level fairness control at decode time, with distribution-free marginal validity guarantees (under exchangeability) for any frozen causal language model. COFT operates in three stages. First, it creates a masked counterfactual prompt by replacing sensitive spans with neutral tokens. Second, it compares the factual and masked logit distributions through lightweight logit fusion to attenuate attribute-driven biases. Third, it uses dual-branch split-conformal calibration to certify per-step candidate token sets at a user-chosen risk level. We evaluate COFT across six models and multiple bias benchmarks. Our method reduces standard bias metrics by 30-55% (median 38%) while preserving task utility and language quality. Reasoning accuracies remain unchanged within run-to-run noise margins. The computational overhead is modest, equivalent to one additional cached forward pass (<=11%). COFT offers a clear, auditable path to safer CoT generation with significant bias reduction, negligible utility loss, and no requirement for retraining, auxiliary classifiers, or weight access.

Arya Fayyazi, Mehdi Kamal, Massoud Pedram

Department of Electrical and Computer Engineering, University of Southern California, Los Angeles, California, USA.

Social Bias in Language Models Counterfactual Fairness Language Model Bias Evaluation Linguistic Bias in Language Models

Ask PDF

May 27, 2026cs.AI

Human-like in-group bias in instruction-tuned language model agents

As autonomous AI agents are deployed in persistent, interacting networks -- coordinating tasks, routing resources, and accumulating reputational histories -- the social dynamics that emerge will determine who receives opportunity and who does not, at scales no human institution can supervise. We ran a controlled multi-agent simulation in which instruction-tuned language model agents interacted across 500 turns under three conditions manipulating group label salience and resource scarcity, across six model families with 20 seeds each. When group labels were visible, we observed in-group trust bias, action homophily, and network assortativity -- all absent when labels were hidden -- a pattern structurally consistent with salience-dependence in human social psychology. This discrimination was invisible to standard action-log audits: bias operated entirely through who received each action, not what actions were chosen, with action-type distributions showing no increase in negative actions across conditions. Per-turn in-group versus out-group differentials of 5 to 16 percentage points were statistically significant for all six models (Wilcoxon signed-rank, all Benjamini-Hochberg-corrected p < 0.001), establishing group-contingent targeting as a robust property of instruction-tuned language models across architectures and training regimes. Compounded through 500 turns of reciprocation, these differentials accumulated into in-group trust biases of +0.014 to +0.100 (d = 0.84-4.52) -- illustrating how modest per-interaction targeting propagates into structural inequality in persistent networks.

Messi H. J. Lee

Independent Researcher · Seoul, South Korea

Social Bias in Language Models Large Language Model-Based Social Simulation Multi-Agent LLMs

Ask PDF

May 27, 2026cs.CL

Auditing Stance Asymmetry in Generative Explanations

Bias evaluation for language models has made substantial progress on bounded comparisons, such as overt derogation, stereotype association, or label-sensitive differences under controlled substitutions. Open-ended explanations raise a different problem: they guide interpretation by assigning responsibility, legitimacy, context, and grievance. A model can avoid hostile language while making one side structurally understandable and another personally at fault, overreacting, or less worth taking seriously. We call this stance-bearing asymmetry in generative explanations. We propose Symmetry Decomposition Evaluation (SDE), which tests paired situations with concrete group labels, structural-role rewrites, and explicit support or counter-evidence. In a controlled 32-family prototype suite, this decomposition shows that surface differences are not all alike: some weaken under structural or evidence control, while others remain as stable differences in how the model assigns blame, context, or legitimacy. Targeted case review and judge comparison suggest a broader difficulty for evaluating open-ended framing asymmetries: judge readings shift across operationalizations, and scalar scores can flatten distinctions that readers use to interpret explanatory stance. SDE therefore reframes generative bias evaluation as an audit of explanatory stance -- what stance each side receives, how it changes under decomposition, and where automatic scoring becomes unstable.

Jiarui Han

Language Model Generation Evaluation Social Bias in Language Models Framing Effects in Language Models Language Model Bias Evaluation Linguistic Bias in Language Models Language Model Auditing

Ask PDF

May 26, 2026cs.CL

Algorithmic Fragility and Persona Bias in LLM-Generated Autistic Communication

Safety alignment reduces explicitly harmful outputs but inadvertently encodes a sanitized, neuronormative representation of marginalized communication. We investigate this encoding using a dual-persona rewrite paradigm, prompting ten large language models (LLMs) to rewrite naturally occurring autistic discourse from either an autistic or neurotypical persona. We uncover autistic-persona rewrites diverge significantly more in lexical form and affective register than neurotypical rewrites, despite equivalent semantic similarity. Furthermore, most models collapse cross-persona generations into near-identical outputs. To uncover the mechanisms behind this generative breakdown, we introduce a multi-agent qualitative analysis framework. Our results reveal systemic output erasure, stereotyped hallucination, and task-evasive meta-commentary are pervasive failure modes for this task that cluster by alignment strategy rather than parameter scale. Finally, our targeted comparison with autistic human annotators demonstrates that community-insider knowledge produces systematic label reversals relative to LLM classifications. Our findings indicate that current alignment training causes persona-specific generative breakdown visible only through qualitative analysis, confirming a deep representational gap that prompt engineering cannot resolve.

Naba Rizvi, Mohammed Rizvi, Harper Strickland +2

University of California · Georgia Institute of Technology · Cardiff University

Autism Spectrum Disorder Social Bias in Language Models LLM Safety Alignment Persona-Conditioned Generation

Ask PDF

May 23, 2026cs.CL

Side-by-side Comparison Amplifies Dialect Bias in Language Models

Language models (LMs) can exhibit biases based on variations in their dialects, even in the absence of a dialect label, a behavior known as covert dialect bias. In this work, we quantify covert dialect bias in online discourse by evaluating how LMs associate stereotypical traits (derived from social psychology research on racial bias) with intent-equivalent tweets in Standard American English (SAE) and African-American Vernacular English (AAVE). While prior work shows that LMs associate more negative stereotypes with AAVE when evaluating tweets in isolation, we are surprised to find that this bias is significantly exacerbated when SAE / AAVE tweet pairs are compared side by side, a setting that more closely reflects high-impact decision making contexts in which models are used to rank candidates. The bias only worsens when dialect labels are explicitly specified. This is striking, given the extensive efforts from commercial developers to mitigate bias in their LMs. Encouragingly, we show that counterfactual fairness finetuning can mitigate covert dialect bias for some stereotypical traits, reducing average disparities when evaluating tweets in isolation, however, these improvements do not consistently hold across traits when evaluating SAE / AAVE tweets side by side. Our findings show that existing evaluation settings for covert dialect bias may underestimate its severity, specifically in contrastive settings. Additionally, overt dialect bias remains pronounced even after safety aligned finetuning, indicating that it remains an unresolved problem, and motivates the need for more robust evaluation and mitigation frameworks.

Kritee Kondapally, Claire J. Smerdon, Pooja C. Patel +5

University of Southern California, USA

Social Bias in Language Models Algorithmic Fairness Language Model Bias Evaluation Linguistic Bias in Language Models

Ask PDF

May 23, 2026cs.LG

Omissive Bias in Religious Representation: Benchmarking LLM Answers to Everyday Ethical Decision-making

As large language models become a default source of guidance on personal, moral, and existential questions, it matters whether they draw on the religious frameworks that have historically shaped such reasoning, or systematically omit them. In this paper, we ask a deliberately narrow question: when posed an everyday ethical question for which religious perspectives may be valuable, do LLMs invoke religion at all? In contrast to benchmarks that look for the presence of political leanings or social bias, we look for the absence of religious representation as a dimension of value alignment and bias in LLMs. We term this ``omissive bias.'' To measure omissive bias, we contribute the AllFaith Religious Representation Benchmark: 150 ethically and personally salient questions, sourced from in-the-wild chat transcripts and faith-community contributors, paired with an LLM-as-judge rubric that gives full credit for any mention of a religion, a religious practice, or a religious leader. The questions are not themselves about religion--they are open-ended questions about grief, forgiveness, relationships, purpose, and honesty, where religion is one valuable perspective among several. We also run a human-subjects survey to compare LLM behavior against human expectations. Evaluating 27 models, we find that LLMs consistently underrepresent religion relative to human expectations. The omission is asymmetric: models invoke religion more readily for abstract existential questions (meaning, death, truth) than for the practical personal situations--grief, marriage, family conflict, addiction--where many people most rely on it. It is not our purpose to adjudicate which values LLMs should hold. We argue, more modestly, that current LLM responses overlook critical opportunities to reflect religious frameworks that many people draw on when navigating personal and ethical challenges.

David Wingate, Sheryl Carty, Joshua Coates +13

1Brigham Young University · 2B. H. Roberts Foundation · 5Yeshiva University +2

Moral Reasoning in Language Models Social Bias in Language Models Language Model Bias Evaluation

Ask PDF

May 21, 2026cs.CL

When AI Takes Sides on Questions of Faith: Persistent Asymmetries in AI-Mediated Faith Guidance

We ask whether large language models (LLMs) treat queries about religious conversion symmetrically. The answer is no. When asked for advice on hypothetical faith transitions from religion A->B vs. religion B->A , models exhibited consistent asymmetries, favoring some religions while subtly discouraging conversion to others. On average Catholic, Bahá'í, and Sikh religions were broadly favored (high support for joining, low support for leaving), while Atheists, Agnostics, and Jehovah's Witnesses were primarily disfavored. Patterns varied by model size and model provider, with Grok 4.20 exhibiting the strongest asymmetries. We tested 20 commercial and open-source language models across 182 religion pairings using a human-verified LLM-as-judge framework. Each model was probed via interactions with a simulated user asking for advice on a potential faith conversion. Models tended to use more encouraging language for some faith transitions over others; these patterns were systematically repeatable across multiple trials. All LLMs tested exhibited reproducible asymmetry, though the pattern of preferences differed for each. Overall preferences persist across multiple question phrasings and variations in the religious pairing dataset. Taken together, these results suggest that asymmetry is a robust property of model behavior rather than an artifact of how the models' answers were scored. It is important to consider that any imbalances deployed and reproduced at scale can have real-world implications.

Brett Israelsen, Sheryl Carty, Josh Coates +3

Brigham Young University · B. H. Roberts Foundation

Social Bias in Language Models Language Model Bias Evaluation

Ask PDF

May 21, 2026cs.CL

Reducing Political Manipulation with Consistency Training

Large language models (LLMs) exhibit systematic political bias across a variety of sensitive contexts. We find that LLMs handle counterpart topics from opposing political sides asymmetrically. We refer to this phenomenon as covert political bias and identify 7 categories of techniques through which it operates. We propose two metrics for covert bias: Sentiment Consistency measures symmetry in rhetoric and framing across paired political prompts; Helpfulness Consistency measures symmetric depth and engagement. To reduce both types of covert bias, we introduce Political Consistency Training (PCT), an RL training method with two complementary paradigms: Sentiment Consistency Training and Helpfulness Consistency Training. We show that PCT preserves overall helpfulness, substantially reduces covert political bias, and generalizes to held-out benchmarks. We release our work at https://political-manipulation.ai

Long Phan, Devin Kim, Alexander Pan +3

Center for AI Safety · UC Berkeley

Social Bias in Language Models Political Bias in Language Models Language Model Bias Evaluation Linguistic Bias in Language Models Language Model Post-Training

Ask PDF

May 19, 2026cs.CY

Occupational Prompting Reveals Cultural Bias in Large Language Models

Social roles shape expectations, priorities, and judgments, yet it remains unclear how large language models (LLMs) associate occupational identities with broader cultural value patterns. Prior work used nationality-based cultural prompting to study how LLM responses to value-survey questions align with human cultural benchmarks. In this paper, we extend that framework by replacing cultural prompting with occupational prompting to examine how professional-role cues influence value-survey responses in open-weight LLMs. Using a survey-grounded evaluation pipeline based on questions from the Integrated Values Surveys, we project model responses into the two-dimensional Inglehart--Welzel cultural space. We prompt open-weight LLMs to answer questions under occupational identities such as accountant, teacher, engineer, and nurse, and then analyze how these occupation-conditioned responses are positioned on the cultural map. Our results show that when open-weight LLMs are prompted with occupations rather than national identities, their responses remain within a broadly Western-leaning region of the cultural map. However, different occupations introduce shifts within this region, producing distinct occupational skews. This indicates that occupational prompts are not treated as neutral role labels, but instead elicit structured value patterns. These findings extend survey-based evaluation of cultural bias beyond nationality-based prompting and provide a framework for studying how occupational personas shape value expression in LLMs.

Maksim E. Eren, Andrea Brennen, Ryan C. Barron +1

Computational Intelligence & Modeling, Los Alamos National Laboratory, Los Alamos, New Mexico, USA. · IQT, USA. · Advanced Research in Cyber Systems, Los Alamos National Laboratory, Los Alamos, New Mexico, USA.

LLM Prompting Social Bias in Language Models Open-Weight Language Models Cultural Bias in Language Models Language Model Bias Evaluation

Ask PDF

May 17, 2026cs.CL

Artificial Intolerance: Stigmatizing Language in Clinical Documentation Skews Large Language Model Decision-Making

Large Language Models (LLMs) are increasingly deployed in high-stakes domains such as clinical decision support and medical documentation. However, the robustness of these models against subtle linguistic variations, specifically stigmatizing language (SL) commonly found in human-authored clinical notes, remains critically under-explored. In this work, we investigate whether frontier LLMs inherit and propagate this human bias when processing clinical text. We systematically evaluate nine frontier LLMs across four stigmatized medical conditions, utilizing clinical vignettes injected with varying intensities and phenotypes of SL (doubt, blame, and maligning). Our results demonstrate that all evaluated models exhibit substantial bias, with clinical decision-making significantly skewed towards less aggressive patient management. Notably, we observe a high sensitivity to linguistic framing, where a single SL sentence is sufficient to alter model outputs, revealing a clear dose-response relationship. Furthermore, we evaluate standard prompt-based mitigation strategies, including Chain-of-Thought (CoT) reasoning and model self-debiasing. These approaches show limited efficacy; models struggle to explicitly identify SL while remaining implicitly influenced by it. Our findings expose a critical vulnerability in current LLMs regarding fairness and robustness in clinical NLP, underscoring the need for rigorous algorithmic guardrails to prevent the automation of health disparities.

Jen-tse Huang, Didi Zhou, Faith Kamau +5

1Johns Hopkins University.

Social Bias in Language Models Clinical Language Model Evaluation Language Model Robustness

Ask PDF

May 16, 2026cs.CL

GPF-LiveNews: A Streaming Evaluation Protocol for Group-Conditioned Framing in Large Language Models

Deployed language models are evaluated in a non-stationary environment: model versions, retrieval layers, safety systems, and real-world inputs all change over time. Static bias benchmarks remain useful, but they do not show how models frame newly emerging events for different prompted audiences. We introduce GPF-LIVENEWS, a streaming evaluation protocol and benchmark snapshot for auditing group-conditioned framing in open-ended LLM outputs. The protocol expands fresh BBC/Reuters news anchors across 42 identity labels and seven prompt families, then evaluates response bundles using semantic-sensitivity and sentiment-disparity signals. In a pilot over 12 monitoring runs and 23 hosted models, Policy/Action prompts produce the strongest semantic movement, while sentiment variation is flatter across dimensions and prompt families. The released artifact includes article metadata, prompt templates, instantiated prompts, model-output metadata, score tables, documentation, and reproduction scripts. We interpret all scores as observed-window audit signals for human review, not as permanent fairness rankings or direct proof of harmful bias.

Mohd Ariful Haque, Fahad Rahman, Kishor Datta Gupta +1

Clark Atlanta University · United International University

LLM Evaluation LLM Auditing Social Bias in Language Models Language Model Bias Evaluation

Ask PDF

May 15, 2026cs.CL

DebiasRAG: A Tuning-Free Path to Fair Generation in Large Language Models through Retrieval-Augmented Generation

Large language models (LLMs) have achieved unprecedented success due to their exceptional generative capabilities. However, because they depend on knowledge encapsulated from training corpora, they may produce hallucinations, stereotypes, and socially biased content. In particular, LLMs are prone to prejudiced responses involving race, gender, and age, which are collectively referred to as social biases. Prior studies have used fine-tuning and prompt engineering to mitigate such biases in LLMs, but these methods require additional training resources or domain knowledge to design the framework. Moreover, they may degrade the original capabilities of LLMs and often overlook the need for dynamic debiasing contexts for fairer inference. In this paper, we propose DebiasRAG, a novel tuning-free and dynamic query-specific debiasing framework based on retrieval-augmented generation (RAG). DebiasRAG improves fairness while preserving the intrinsic properties of LLMs, such as representation ability. DebiasRAG consists of three stages: (1) query-specific debiasing candidate generation; (2) context candidate pool construction; and (3) gradient-updated debiasing-guided context piece reranking. First, DebiasRAG leverages self-diagnosed bias contexts relevant to the query through regular retrieval, where the bias contexts are prepared offline by the DebiasRAG provider. Given the query-specific bias contexts, DebiasRAG reversely produces debiasing contexts, which are provided as additional fairness constraints for LLM outputs. Second, a regular RAG retrieval process produces query-related contexts from the regular RAG document database, such as a chunked Wikipedia dataset.

Rui Chu, Bingyin Zhao, Thanh Quoc Hung Le +6

Retrieval-Augmented Generation Debiased ML Social Bias in Language Models

Ask PDF

May 13, 2026cs.SI

When Do LLMs Generate Realistic Social Networks? A Multi-Dimensional Study of Culture, Language, Scale, and Method

Large language models (LLMs) are increasingly used as substitutes for human subjects in behavioral simulations, including synthetic social network generation. Yet it remains unclear how their relational outputs depend on prompt design, cultural framing, prompt language, and model scale. Building on homophily theory and structural balance theory, we formalize four LLM-based tie-formation mechanisms: sequential, global, local, and iterative, and treat them as distinct conditional distributions over edge sets. Using a fixed roster of 50 demographically grounded personas, we generate 192 verified directed networks across four cultural contexts, four prompt languages, three GPT-4.1 variants, and four prompting architectures, with two seeds per condition. We find that cultural framing shifts inbreeding homophily and largest-component connectivity. Political affiliation dominates tie formation under three methods, while the global method substitutes age, showing that prompt architecture functions as a substantive sociological variable. Model scale produces a stable divergence ranking, with the smallest variant behaving qualitatively differently rather than merely noisily. Prompt language alone sharply shifts religion homophily, especially under Hindi prompting, while leaving political homophily nearly invariant. LLM-generated networks match real social graphs on clustering and modularity better than standard graph baselines, yet encode demographic biases above empirical levels. These results show that prompt choices often treated as implementation details encode substantive sociological assumptions.

Sai Hemanth Kilaru, Sriram Theerdh Manikyala, Raghav Upadhyay +3

University of Arizona. Tucson, AZ 85721

LLM Prompting Social Bias in Language Models Synthetic Data Generation Cultural Bias in Language Models Large Language Model-Based Social Simulation Demographic Bias in Language Models

Ask PDF

May 12, 2026cs.AI

DisaBench: A Participatory Evaluation Framework for Disability Harms in Language Models

General-purpose safety benchmarks for large language models do not adequately evaluate disability-related harms. We introduce DisaBench: a taxonomy of twelve disability harm categories co-created with people with disabilities and red teaming experts, a taxonomy-driven evaluation methodology that pairs benign and adversarial prompts across seven life domains, and a dataset of 175 prompts with human-annotated labels on 525 prompt-response pairs. Annotation by four evaluators with lived disability experience reveals three findings: harm rates vary sharply by disability type and will compound in non-text modalities, terminology-driven harm is culturally and temporally bound rather than universally assessable, and standard safety evaluation catches overt failures while missing the subtle harms that only domain expertise can recognize. Disability harm is simultaneously personal, intersectional, and community-defined: it cannot be isolated from the full context of who a person is, and general-purpose benchmarks systematically miss it. We will release the dataset, taxonomy, and methodology via Hugging Face and an open-source red teaming framework for direct integration into existing safety pipelines with no additional infrastructure.

Eugenia Kim, Ioana Tanase, Christina Mallon

Microsoft

LLM Safety Benchmarks LLM Evaluation Language Model Safety Evaluation Social Bias in Language Models Human-in-the-Loop Evaluation

Ask PDF

May 12, 2026cs.CY

Two Wrongs, No Right: Auditing Social-Desirability Bias in LLM Annotators for Computational Social Science

LLM annotators are increasingly used in computational social science (CSS), but it is unclear whether their alignment-shaped errors preserve the empirical conclusions a researcher would report. We audit three open-source 7B instruction-tuned models (Zephyr, Mistral-Instruct, Qwen2.5-Instruct) across six TweetEval tasks under four prompt conditions (72 cells) and find that social-desirability failures do not run in a single direction. Zephyr exhibits leniency bias, systematically under-applying harmful labels (offensive language: false benign rate 0.729, false alarm rate 0.031). Mistral and Qwen exhibit overcorrection, over-applying the same labels (Mistral hate-speech FAR = 0.604). All three models exhibit neutrality bias on abortion stance, underestimating opposition prevalence by 24 to 40 percentage points and inflating the neutral label. None of the four prompting interventions we test (neutral, safety framing, depersonalized, chain-of-thought) corrects these failures across models; safety framing can worsen stance distortion. Strikingly, Zephyr's hate-speech prevalence estimate matches the gold rate exactly while its class-conditional errors are large in both directions, an accidental cancellation that misleads aggregate validation. We translate these patterns into a three-part taxonomy with diagnostic FBR/FAR signatures and a lightweight gold-sample validation protocol. The headline for trustworthy CSS: a model that looks calibrated on aggregate metrics can still flip the substantive empirical conclusion a researcher would report.

Varun Kotte

Independent Researcher

Social Bias in Language Models LLM-Assisted Annotation Computational Social Science Language Model Bias Evaluation

Ask PDF

May 11, 2026cs.GT

When to Ask a Question: Understanding Communication Strategies in Generative AI Tools

Generative AI models differ from traditional machine learning tools in that they allow users to provide as much or as little information as they choose in their inputs. This flexibility often leads users to omit certain details, relying on the models to infer and fill in under-specified information based on distributional knowledge of user preferences. Such inferences may privilege majority viewpoints and disadvantage users with atypical preferences, raising concerns about fairness. Unlike more traditional recommender systems, LLMs can explicitly solicit more information from users through natural language. However, while directly eliciting user preferences could increase personalization and mitigate inequality, excessive querying places a burden on users who value efficiency. We develop a stylized model of user-LLM interaction and develop an objective that captures tradeoff between user burden and preference representation. Building on the observation that individual preferences are often correlated, we analyze how AI systems should balance inference and elicitation, characterizing the optimal amount of information to solicit before content generation. Ultimately, we show that information elicitation can mitigate the systematic biases of preference inference, enabling the design of generative tools that better incorporate diverse user perspectives while maintaining efficiency. We complement this theoretical analysis with an empirical evaluation illustrating the model's predictions and exploring their practical implications.

Charlotte Park, Kate Donahue, Manish Raghavan

Massachusetts Institute of Technology Cambridge, Massachusetts, USA

Social Bias in Language Models Algorithmic Fairness User Preference Modeling Preference Elicitation

Ask PDF

May 11, 2026cs.CL

How Does Differential Privacy Affect Social Bias in LLMs? A Systematic Evaluation

Large language models (LLMs) trained on web-scale corpora can memorize sensitive training data, posing significant privacy risks. Differential privacy (DP) has emerged as a principled framework that limits the influence of individual data points during training, yet the relationship between differential privacy and social bias in LLMs remains poorly understood. To investigate this, we present a systematic evaluation of social bias in a pretrained LLM trained with DP-SGD, comparing a DP model against non-DP baselines across four complementary paradigms: sentence scoring, text completion, tabular classification, and question answering. We find that DP reduces bias in sentence scoring tasks, where bias is measured through controlled likelihood comparisons, yet this improvement does not generalize across all tasks. Our results reveal a discrepancy between logit-level bias and output-level bias. Moreover, decreasing memorization does not necessarily reduce unfairness, underscoring the importance of multi-paradigm evaluation when assessing fairness in LLMs.

Eduardo Tenorio, Karuna Bhaila, Xintao Wu

University of Arkansas

Social Bias in Language Models Language Model Bias Evaluation Differential Privacy

Ask PDF

May 11, 2026cond-mat.stat-mech

Collective Alignment in LLM Multi-Agent Systems: Disentangling Bias from Cooperation via Statistical Physics

We investigate the emergent collective dynamics of LLM-based multi-agent systems on a 2D square lattice and present a model-agnostic statistical-physics method to disentangle social conformity from intrinsic bias, compute critical exponents, and probe the collective behavior and possible phase transitions of multi-agent systems. In our framework, each node of an

L\!\times\!L

lattice hosts an identical LLM agent holding a binary state (

+1

-1

, mapped to yes/no) and updating it by querying the model conditioned on the four nearest-neighbor states. The sampler temperature

T

serves as the sole control parameter. Across three open-weight models (llama3.1:8b, phi4-mini:3.8b, mistral:7b), we measure magnetization and susceptibility under a global-flip protocol designed to probe

\mathbb{Z}_2

symmetry. All models display temperature-driven order-disorder crossovers and susceptibility peaks; finite-size scaling on even-

L

lattices yields effective exponents

γ/ν

whose values are model-dependent, close to but incompatible with the 2D Ising universality class (

γ/ν=7/4

). Our method enables the extraction of effective

β

-weighted couplings

\tilde{J}(T)

and fields

\tilde{h}(T)

, which serve as a measure of social conformity and intrinsic bias. In the models we analyzed, we found that collective alignment is dominated by an intrinsic bias (

\tilde{h}\gg\tilde{J}

) rather than by cooperative neighbor coupling, producing field-driven crossovers instead of genuine phase transitions. These effective parameters vary qualitatively across models, providing compact collective-behavior fingerprints for LLM agents and a quantitative diagnostic for the reliability of multi-agent consensus and collective alignment.

Cristiano De Nobili

Critiqality, Milan, Italy

Multi-Agent LLM Systems Multi-Agent Coordination Opinion Dynamics Social Bias in Language Models Phase Transitions Multi-Agent Systems+1

Ask PDF

May 11, 2026cs.CY

StereoTales: A Multilingual Framework for Open-Ended Stereotype Discovery in LLMs

Multilingual studies of social bias in open-ended LLM generation remain limited: most existing benchmarks are English-centric, template-based, or restricted to recognizing pre-specified stereotypes. We introduce StereoTales, a multilingual dataset and evaluation pipeline for systematically studying the emergence of social bias in open-ended LLM generation. The dataset covers 10 languages and 79 socio-demographic attributes, and comprises over 650k stories generated by 23 recent LLMs, each annotated with the socio-demographic profile of the protagonist across 19 dimensions. From these, we apply statistical tests to identify more than 1{,}500 over-represented associations, which we then rate for harmfulness through both a panel of humans (N = 247) and the same LLMs. We report three main findings. \textbf{(i)} Every model we evaluate emits consequential harmful stereotypes in open-ended generation, regardless of size or capabilities, and these associations are largely shared across providers rather than isolated misbehaviors. \textbf{(ii)} Prompt language strongly shapes which stereotypes appear: rather than transferring as a shared set of biases, harmful associations adapt culturally to the prompt language and amplify bias against locally salient protected groups. \textbf{(iii)} Human and LLM harmfulness judgments are broadly aligned (Spearman

ρ=0.62

), with disagreements concentrating on specific attribute classes rather than specific providers. To support further analyses, we release the evaluation code and the dataset, including model generations, attribute annotations, and harmfulness ratings.

Pierre Le Jeune, Étienne Duchesne, Weixuan Xiao +4

Giskard AI · École Normale Supérieure, INSERM, Paris

Open-Ended Generation Multilingual Language Model Evaluation Language Model Generation Evaluation Social Bias in Language Models Cultural Bias in Language Models Language Model Bias Evaluation

Ask PDF

May 9, 2026cs.CL

Fin-Bias: Comprehensive Evaluation for LLM Decision-Making under human bias in Finance Domain

Large language models (LLMs) are increasingly deployed in financial contexts, raising critical concerns about reliability, alignment, and susceptibility to adversarial manipulation. While prior finance-related benchmarks assess LLMs' capabilities in stock trading, they are often restricted to small sample and fail to demonstrate LLM susceptibility to context with potential human bias. We introduce Fin-Bias (financial herding under long and uncertain financial context), a benchmark for evaluating LLM investment decision-making when faced with uncertainty and possible human-biased opinions. Fin-Bias includes 8868 long firm-specific analyst reports, including firm aspects summarized and analyzed by sophisticated analysts with investment ratings (Bullish/Neutral/Bearish) spanning from various industries. We present large language models with firm analyst reports with/without analyst investment ratings and even with 'fake' rating, to get investment ratings generated by LLMs. Our results reveal that LLMs tend to herd the explicit bias in context. We also develop a method to detect potential human opinions, which can encourage LLMs to think independently, some models even exceed human performance in predicting future stock return.

Xiaoyu Hu, Jinman Zhao

Rutgers University · Department of Computer Science, University of Toronto

LLM Evaluation Social Bias in Language Models LLM Decision-Making Finance

Ask PDF

May 6, 2026cs.CL

Misaligned by Reward: Socially Undesirable Preferences in LLMs

Reward models are a key component of large language model alignment, serving as proxies for human preferences during training. However, existing evaluations focus primarily on broad instruction-following benchmarks, providing limited insight into whether these models capture socially desirable preferences. As a result, important failures in social alignment can remain hidden. We extend reward-model benchmarking to four socially consequential domains: bias, safety, morality, and ethical reasoning. We introduce a framework that converts social evaluation datasets into pairwise preference data, leveraging gold labels where available and directional bias indicators otherwise. This enables us to test whether reward models prefer socially undesirable responses, and whether their preferences produce systematically biased distributions over selected outputs. Across five publicly available reward models and two instruction-tuned models used as reward proxies, we find substantial variation across domains, with no single model performing best overall. The models fall well short of strong social intelligence: they often prefer socially undesirable options, and their preferences produce systematically biased distributions. Moreover, stronger bias avoidance can reduce sensitivity to context, revealing a key alignment trade-off between avoiding biased outcomes and preserving contextual faithfulness. These findings show that standard reward benchmarks are insufficient for assessing social alignment and highlight the need for evaluations that directly measure the social preferences encoded in reward models.

Gayane Ghazaryan, Esra Dönmez

Institute for Natural Language Processing, University of Stuttgart · 2Interchange Forum for Reflecting on Intelligent Systems, University of Stuttgart

Reward Modeling Language Model Safety Evaluation Social Bias in Language Models Preference Alignment Reward Model Evaluation

Ask PDF

May 5, 2026cs.CL

EQUITRIAGE: A Fairness Audit of Gender Bias in LLM-Based Emergency Department Triage

Emergency department triage assigns patients an acuity score that determines treatment priority, and clinical evidence documents persistent gender disparities in human acuity assessment. As hospitals pilot large language models (LLMs) as triage decision support, a critical question is whether these models reproduce or mitigate known biases. We present EQUITRIAGE, a fairness audit of LLM-based ESI assignment evaluating five models (Gemini-3-Flash, Nemotron-3-Super, DeepSeek-V3.1, Mistral-Small-3.2, GPT-4.1-Nano) across 374,275 evaluations on 18,714 MIMIC-IV-ED vignettes under four prompt strategies. Of 9,368 originals, 9,346 are paired with a gender-swapped counterfactual. All five models produced flip rates above a pre-registered 5% threshold (9.9% to 43.8%). Two showed directional female undertriage (DeepSeek F/M 2.15:1, Gemini 1.34:1); two were near-parity; one had high sensitivity with weak male-direction asymmetry. DeepSeek's directional bias coexisted with a low outcome-linked calibration gap (0.013 against MIMIC-IV admission), a Chouldechova-style dissociation between within-group calibration and between-pair counterfactual invariance. Demographic blinding reduced Gemini's flip rate to 0.5%; an age-preserving blind variant left DeepSeek with residual F/M 1.25, implicating age as a residual channel. Chain-of-thought prompting degraded accuracy for all five models. A two-model ablation reveals opposite underlying mechanisms for the same directional phenotype: in Gemini the signal is emergent in the combined name+gender swap, while in DeepSeek the gender token alone carries it. EQUITRIAGE shows that group parity, counterfactual invariance, and gender calibration are distinct fairness properties, that intervention effectiveness is model-dependent, and that per-model counterfactual auditing should precede clinical deployment.

Richard J. Young, Alice M. Matthews

University of Nevada, Las Vegas, Lee Business School, Las Vegas, NV, USA · DeepNeuro AI, Las Vegas, NV, USA · Concorde Career Colleges, Dept. of Cardiovascular and Medical Diagnostic Sonography

Gender Bias in Language Models Clinical Triage Social Bias in Language Models Clinical Decision-Making Language Model Calibration Language Model Bias Evaluation+1

Ask PDF

May 4, 2026cs.LG

Moral Sensitivity in LLMs: A Tiered Evaluation of Contextual Bias via Behavioral Profiling and Mechanistic Interpretability

Large language models (LLMs) are increasingly deployed in settings that require nuanced ethical reasoning, yet existing bias evaluations treat model outputs as simply "biased" or "unbiased." This binary framing misses the gradual, context-sensitive way bias actually emerges. We address this gap in two stages: behavioral profiling and mechanistic validation. In the behavioral stage, we introduce the Moral Sensitivity Index (MSI), a metric that quantifies the probability of biased output across a graduated, seven-tier stress test ranging from abstract numerical problems to scenarios rooted in historical and socioeconomic injustice. Evaluating four leading models (Claude 3.5, Qwen 3.5, Llama 3, and Gemini 1.5), we identify distinct behavioral signatures shaped by alignment design: for instance, Gemini 1.5 reaches 72.7% MSI by Tier 5 under socioeconomic framing, while Claude exhibits sharp suppression consistent with identity-based safety training. We then verify these behavioral patterns mechanistically. We select criminal-bias scenarios, which produced the highest MSI scores across models, as probes and apply logit lens, attention analysis, activation patching, and semantic probing to a controlled set of six models spanning three capability tiers: small language models (SLMs), instruction-tuned base models, and reasoning-distilled variants. Circuit-level analysis reveals a U-curve of bias: SLMs exhibit strong criminal bias; scaling to instruction-tuned models eliminates it; reasoning distillation reintroduces bias to SLM-like levels despite identical parameter counts, suggesting distillation compresses reasoning traces in ways that reactivate shallow statistical associations. Critically, the socially loaded cues that drive high MSI scores activate the same bias-driving circuits identified mechanistically, providing cross-stage validation.

Yash Aggarwal, Atmika Gorti, Vinija Jain +3

University of Maryland, College Park · 2Purdue University · 3Meta +5

Moral Reasoning in Language Models Social Bias in Language Models LLM Interpretability Language Model Bias Evaluation

Ask PDF

May 4, 2026cs.CL

Decoding-Time Debiasing via Process Reward Models: From Controlled Fill-in to Open-Ended Generation

Large language models pick up social biases from the data they are trained on and carry those biases into downstream applications, often reinforcing stereotypes around gender, race, religion, disability, age, and socioeconomic status. The standard fixes (retraining on curated data or fine-tuning with human feedback) are expensive, need access to model weights, and risk degrading the model on other tasks. In this paper we take a different route: we debias the model at decoding time, treating bias mitigation as a structured search over candidate tokens without ever touching model weights. A separate Process Reward Model (PRM) acts as a judge, scoring each candidate for both fairness and fluency. We design three schemes of increasing sophistication (Best-of-N selection, Sequential critique-and-revise, and Constitutional self-audit) and evaluate them on four models (GPT-4o-mini, Llama 3.2 3B, Gemma 3 4B, Qwen 2.5 3B) across a 200-prompt bilingual benchmark in English and Urdu covering eight bias categories. Sequential debiasing proves the most effective, raising mean bias scores by up to +0.40 over baseline while preserving (and sometimes improving) fluency. We then extend all three schemes to open-ended generation, where each token is debiased on the fly, and introduce a lightweight Bias Guard gate that fires only on potentially biased words, keeping overhead near 2x for well-calibrated models. A formal overhead metric that separates generator cost from judge cost reveals that Best-of-N is effectively free on the generator side in a native implementation. GPT-4o-mini, included as a strong proprietary anchor, confirms that the framework scales with model capability; the three open-weight models show where current small-scale LLMs still struggle.

Muneeb Ur Raheem Khan

Lahore University of Management Sciences (LUMS)

Debiased ML Language Model Decoding Process Reward Models Social Bias in Language Models Language Model Bias Evaluation Linguistic Bias in Language Models

Ask PDF

May 2, 2026cs.AI

Truth or Tribe: How In-group Favoritism Prioritize Facts in Persona Agents

In-group favoritism refers to the phenomena of favoring members of one's in-group over out-group members and is widely observed in numerous social cooperative behaviors. Recently, in-group favoritism biases have also been identified in generative language models. However, whether the in-group favoritism exists when persona agents are faced with contradicting information (e.g., misinformation), and how to mitigate the adverse effects of in-group favoritism biases in persona agents have been understudied. To address these problems, we propose a Truth or Tribe simulation framework to study the agent cooperation within the spread of contradicting information through a triadic interaction paradigm, and conduct controlled trials to evaluate the primary moderating factors. Extensive results showcase that persona agents display strong in-group favoritism, accepting incorrect answers from identity-similar peers at much higher rates than from dissimilar peers. In-group favoritism continues to emerge in defeasible reasoning contexts where no absolute truth exists, and it intensifies as cognitive complexity increases. Furthermore, three intervention strategies--Identity-Blind Instruction, Structured Counterfactual Reasoning, and Heterogeneous Perspective Ensemble--are proposed to mitigate the in-group favoritism.

Shijun Lei, Hongyu Wang, Yunji Liang +3

Northwestern Polytechnical University · Central University of Finance and Economics

Knowledge Conflicts in Language Models Social Bias in Language Models Multi-Agent Reasoning

Ask PDF

May 2, 2026cs.LG

Quantization Undoes Alignment: Bias Emergence in Compressed LLMs Across Models and Precision Levels

Large Language Models are routinely compressed via post-training quantization to reduce inference costs and memory footprint for cloud and edge deployment, yet the impact of this compression on model quality remains poorly understood. Existing studies typically compare only two conditions (full-precision vs. a single quantized variant), rely on aggregate bias metrics, and evaluate a single model family, making it impossible to distinguish gradual degradation from threshold-dependent safety failures. We conduct a controlled empirical study of three instruction-tuned models (Qwen2.5-7B, Mistral-7B, Phi-3.5-mini) at five precision levels (BF16 through 3-bit) on 12,148 BBQ bias benchmark items across 5 random seeds, totaling 911,100 inference records. Our results reveal that 3-bit quantization causes 6-21% of previously unbiased items to develop new stereotypical behaviors, following a clear dose-response pattern confirmed via logistic regression, while models' willingness to select "unknown" answers declines by 17.4%. Crucially, these item-level changes are invisible to standard quality metrics: perplexity increases by less than 0.5% at 8-bit and under 3% at 4-bit across all three models, yet 2.5-5.6% of items already develop new biases at 4-bit. These findings demonstrate that aggregate evaluation metrics systematically miss fairness-critical degradation, underscoring the need for quality-aware compression protocols that explicitly test for bias emergence before deployment.

Plawan Kumar Rath, Rahul Maliakkal

Weight Pruning Amplifies Bias: A Multi-Method Study of Compressed LLMs for Edge AI

Weight pruning is widely advocated for deploying Large Language Models on resource-constrained IoT and edge devices, yet its impact on model fairness remains poorly understood. We conduct a controlled empirical study of three instruction-tuned models (Gemma-2-9b-it, Mistral-7B-Instruct-v0.3, Phi-3.5-mini-instruct) across three pruning methods (Random, Magnitude, Wanda) at four sparsity levels (10-70%) on 12,148 BBQ bias benchmark items with 5 random seeds, totaling 2,368,860 inference records. Our results reveal a Smart Pruning Paradox: activation-aware pruning (Wanda) preserves perplexity nearly perfectly (just 3.5% increase at 50% sparsity for Mistral-7B), yet produces the highest bias amplification, with Stereotype Reliance Score increasing 83.7% and 47-59% of previously unbiased items developing new stereotypical behaviors at 70% sparsity. Random pruning destroys language capability entirely (perplexity exceeding

10^4

and reaching

10^8

) but produces only random-chance bias. We further show that unstructured pruning provides zero storage savings and zero inference latency reduction on real edge hardware, undermining the primary motivation for its use in IoT deployment. Of 180 dense-vs-pruned comparisons, 141 (78.3%) are significant (

p < 0.05

) with mean

|h| = 0.305

. Published quantization studies report up to 21% of responses flipping between biased and unbiased states; our pruning results show transition rates nearly three times higher (47-59%), suggesting pruning poses a categorically greater risk to alignment than quantization. These findings demonstrate that perplexity-based evaluation provides false assurance of behavioral equivalence, and that IoT deployment pipelines require bias-aware validation before deploying pruned models at the edge.

Plawan Kumar Rath, Rahul Maliakkal

Momentum

Related topics

Latest papers 126