Stereotype Mitigation

Counterspeech (CS) - direct responses that counter online Hate Speech (HS) using reasoning and alternative viewpoints - has emerged as an alternative to content removal. Current automatic CS generation methods, however, frequently produce generic, ineffective replies that fail to target the implicit stereotypes behind HS. To bridge this gap, we propose a novel scope-conditioned generation framework that explicitly integrates structured stereotype characteristics into Large Language Models prompts. We validate our approach on a novel, human-curated dataset annotated in English, Italian, and Spanish. Extensive evaluations show that stereotype-conditioned prompting substantially outperforms generic baselines across all three languages, obtaining significant gains in factuality, specificity, cogency, and effectiveness for both explicit and implicit implied stereotypes.

Commercial text-to-image systems silently revise user prompts before generating images, a step users typically cannot disable or even see. Yet, existing audits of cultural bias examine only the final images and treat generation as a single pipeline, so they cannot tell where the bias originates. We introduce WORLDVIEW, a multilingual benchmark of 8,960 prompts across 15 languages and 31 language-context pairings. Using it, we audit the revision layer in three systems (DALL-E-3, Imagen-4, GPT-Image-1.5) through a three-step analysis of how heavily it marks each cultural context, whether it flattens that context into a narrow vocabulary, and whether that vocabulary is stereotypical. Relative to a no-context English baseline, the US is the least-marked context, while non-Western and non-Anglophone contexts are marked far more heavily, flattened into narrow vocabularies applied across topically diverse prompts, and reduced to recognizable cultural stereotypes. Comparing images from original versus revised prompts on models without a revision layer, we identify the layer itself as a previously undocumented, causal source of this stereotyping. To locate cultural bias, and fix it, we must audit the system as deployed, not the model alone.

Large language models are increasingly used as judges to measure social bias in text, yet the passages they judge are often noisy, containing typos, informal spelling, and broken punctuation. The consequences of such surface noise for social bias measurement remain unclear. To investigate this question, we apply five realistic noise conditions at multiple intensity levels to 3,822 stereotype-related responses and compare the resulting bias judgments with those on the original text. We find that such surface noise does not degrade bias measurement symmetrically: it is far more likely to turn neutral judgments into biased ones than biased judgments into neutral ones, by up to a 120x margin. We further observe two non-obvious effects across four LLM judges: in the most fragile judge the distortion is at its purest at mild, realistic noise levels, where erasure is scarcest, and as judges grow robust it attenuates toward parity rather than reversing. Bias measured on noisy text is therefore systematically overestimated, most in the categories that matter most for fairness.

Speech-to-speech (S2S) models now run inside dubbing, translation, and voice agents. Unlike text models, they hear the speaker's voice, which carries the speaker's gender. A faithful system should treat a speaker as who they sound like, not as whoever usually says what they said. Testing this is harder than it looks, since most S2S models answer in a single, fixed output voice, hard-coded so it cannot drift toward a stereotype. Checking the output voice comes back clean even when the model is biased. We therefore ask two questions. When a model re-speaks the input, does the stereotype in the words shift the perceived gender of the output voice (voice rendering)? And when the model states the speaker's gender, does it follow the voice or the content (gender attribution)? We answer both with one controlled experiment crossing male and female voices with masculine-, neutral-, and feminine-stereotyped passages, on five open- and closed-source models in English, Spanish, and Mandarin. The rendered voice shows no stereotype drift. But every model decides the speaker's gender from the content, not the voice. Making the content one step more feminine (masculine -> neutral -> feminine) multiplies the odds of a "female" judgment by 1.7-24. When the content clashes with the voice, the worst model misgenders the speaker in 90% of cases. When they agree, it misgenders in only 2%. The bias thus hides in gender attribution, where fixed-voice evaluation cannot see, and where audits must look as S2S systems increasingly speak for real people.

Multilingual LLMs show stereotype-related behavior that varies across languages, but behavioral scores do not show where the relevant information is represented or how it affects the output. To investigate these internal mechanisms, we compare linear probing, attribution patching, sparse autoencoders (SAEs) and feature ablation in Llama-3.1-8B, Qwen3-8B, and Gemma-2-9B. Probe performance peaks substantially earlier than attribution in all three models, with a separation of 36-53% of model depth. Retained Llama-Scope features often match the social category on which they were selected and form recurring semantic families, but their lexical alignment and ablation effects vary across SAE suites. Only 6-18% of evaluated residual-stream features have language-agnostic effects under our criterion, and none are category-agnostic. Language-agnostic features have larger mean ablation effects in Llama-Scope, but this pattern does not repeat in the other SAE suites. Decodability, output influence, and cross-lingual ablation effects therefore need to be measured separately.

When a question has valid answers under different normative frameworks, a language model must decide which framework to use and whether it can answer correctly within it. We call this setting normative pluralism and study it in Islamic finance using a four-choice taxonomy that separates framework selection from within-framework correctness. This separation reveals the stereotype trap: a cultural cue steers a model toward one framework, but the model selects an incorrect answer within that framework. Across twelve models, two languages, and fifty demographic signals, cultural cues change framework selection and reveal substantial differences in accuracy, especially among non-frontier models. Under the strongest signal, large open-weight models select the Islamic framework 97% of the time. A two-choice evaluation would report near-perfect alignment, although 57--66% of those selections are incorrect. These findings motivate, but do not directly test, the competence-conditioned routing hypothesis: models may favor frameworks where they are more accurate, while cultural cues may expose framework-specific competence gaps.

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.

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

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.

LLMs encode, convey, and perpetuate stereotypes. Prior computational research focuses on a small set of semantic axes investigated in social psychology, and operates on word embeddings produced by language models, leaving open which other semantic axes carry stereotypical associations in LLMs and how LLMs internally represent such axes. We introduce STEREODISCO, a framework that adapts the semantic differential method (Osgood et al., 1957) to the systematic study of stereotypes in LLM internal representations. STEREODISCO constructs approx. 2,000 candidate semantic axes from WordNet antonym synsets, recovers each as a geometric axis in the LLM's activation space via probing, and identifies stereotypical axes via a statistical test over concept projections. As a case study, we apply STEREODISCO to social group stereotypes with LLAMA-3-8B-INSTRUCT and MISTRAL-7B-INSTRUCT. We find that the two LLMs agree with each other on social group ratings more than with humans, suggesting that LLM-encoded stereotype content diverges from that documented in social psychology. We also discover stereotypical axes not investigated in prior work -- including humble vs. proud, narrow-minded vs. broad-minded, and cowardly vs. brave, which human annotators independently confirm.

Regional bias in large language models (LLMs) may shape both perceptions of regional groups and decisions about individuals from different regions. Yet existing studies often examine these manifestations separately, leaving their structure and consequences unclear. We introduce Stereotypes-to-Decisions (S2D), a systematic framework evaluating regional bias from abstract stereotypes to concrete social decisions. Covering all 34 provincial-level administrative regions of China, S2D evaluates six LLMs using stereotype ratings of Warmth (perceived friendliness and trustworthiness) and Competence (perceived capability and intelligence), along with paired-choice tasks across Education, Occupation, and Social Interaction. Results reveal substantial regional differences in regional scores, with considerable agreement across models, especially for Competence and Occupation decisions. Furthermore, these patterns are associated with regional economic and digital development indicators and display mixed human-like stereotypes, with some regions rated highly on one dimension but poorly on the other. They also remain largely stable across Chinese and English prompts. Overall, our findings show that regional bias in LLMs is prevalent, systematic, and consequential, motivating more regionally aware evaluation and mitigation.

Large language models may infer demographic attributes from subtle linguistic cues even when those attributes are not explicitly stated. This pilot study examines whether Qwen2.5-7B-Instruct internally represents Colombian identity, socioeconomic status, or stereotype-related information when processing Colombian-Spanish and English prompts. We use Natural Language Autoencoders (NLA) to verbalize residual-stream activations from layer 20 across four positional quartiles per prompt. Our dataset contains 30 prompts arranged as 15 matched Spanish-English pairs, spanning explicit Colombian cues, implicit Colombian cues, and neutral controls. We report descriptive rates and qualitative evidence rather than statistically powered effects, focusing on whether latent nationality or stereotype representations appear before they are verbalized in the model output. This work connects activation-level interpretability with bias evaluation for underrepresented Spanish varieties.

Text-to-image (T2I) models have been shown to exhibit social biases. Prior work has mainly focused on gender, skin tone, and cultural representation within restricted occupational associations, and emerging benchmarks increasingly incorporate these dimensions. However, disability remains systematically underexplored. Current evaluation practices often fail to align with sociologically grounded definitions of stereotyping, limiting principled assessment of representational harms toward people with disabilities (PWD). To address this, we introduce INCLUDE-BENCH, the first large-scale benchmark for evaluating disability-related bias in T2I models. INCLUDE-BENCH comprises 119K generated images based on prompt design across multiple bias dimensions and both static and dynamic contexts. We evaluate 15 open-source and 2 closed-source models. Our key findings reveal that: (1) mobility-impaired and default disability prompts predominantly yield wheelchair depictions across all models; (2) disability-conditioned generations consistently exhibit less diversity; (3) stereotypical portrayals demonstrate stronger disability-text alignment; and (4) we introduce the Stereotype Content Model (SCM) Score, demonstrating that T2I models reflect real-world stereotypical associations.

Preprocessing-based methods for stereotype mitigation, such as pre-/post-training on debiased corpora, are widely used in NLP. While these approaches reduce measurable stereotypes for targeted groups, we find they often induce unintended shifts-side effects, where stereotyping or counter-stereotyping can increase relative to neutral baselines for other demographics, including across unrelated demographic categories. We demonstrate these side effects across two model families (encoder-only and decoder-only), multiple preprocessing strategies (removing stereotypical sentences, removing group mentions, and swapping group references), and both pre- and post-training at different data scales on Wikipedia. Standard benchmarks frequently miss these shifts. Using attention-rollout analysis, we observe that such side effects are not accompanied by large changes in attention flow, complicating mechanistic explanations. We discuss implications for evaluation, provide actionable diagnostics, and argue for side-effect-aware, transparent mitigation practices.

Research on stereotypes in large language models (LLMs) has largely focused on English-speaking contexts, due to the lack of datasets in other languages and the high cost of manual annotation in underrepresented cultures. To address this gap, we introduce a cost-efficient human-LLM collaborative annotation framework and apply it to construct EspanStereo, a Spanish-language stereotype dataset spanning multiple Spanish-speaking countries across Europe and Latin America. EspanStereo captures both well-documented stereotypes from prior literature and culturally specific biases absent from English-centric resources. Using LLMs to generate candidate stereotypes and in-culture annotators to validate them, we demonstrate the framework's effectiveness in identifying nuanced, region-specific biases. Our evaluation of Spanish-supporting LLMs using EspanStereo reveals significant variation in stereotypical behavior across countries, highlighting the need for more culturally grounded assessments. Beyond Spanish, our framework is adaptable to other languages and regions, offering a scalable path toward multilingual stereotype benchmarks. This work broadens the scope of stereotype analysis in LLMs and lays the groundwork for comprehensive cross-cultural bias evaluation.

Text-to-image diffusion models achieve impressive visual quality, yet demographic bias remains a challenge, as neutral prompts consistently produce stereotypical representations across gender and race. Existing approaches remain limited by costly retraining or by inference-time interventions that often degrade image quality and semantic alignment. We propose Text Embedding Steering (TES), a training-free framework that mitigates demographic bias by directly optimizing conditional text embeddings during the diffusion process. We show that a two-stage strategy - early-stage global alignment followed by iterative denoising-time refinement with CLIP-based feedback - enables stable and controllable attribute steering without modifying model parameters. Extensive experiments on Stable Diffusion demonstrate that TES outperforms existing training-free baselines in fairness while maintaining competitive image quality. These results highlight that inference-time text embedding optimization is a practical and scalable solution for fairness-aware generation in diffusion models.

Warning: This paper contains several toxic and offensive statements. While reasoning generally improves fairness in recent large language models (LLMs), failures persist. In this work, we identify a failure mode, deductive stereotyping, in which models apply population-level statistical regularities to individual cases, producing logically coherent yet socially biased inferences. We provide a statistical interpretation of this phenomenon. To steer models toward fairness-aware reasoning, we propose a reasoning-time injection framework. We further introduce Fair-GCG to systematically discover effective injection phrases. Injection phrases discovered by Fair-GCG improve performance across multiple fairness benchmarks, generalize from smaller to larger LLMs, improves reasoning-level fairness, reduces bias in open-ended generation, and transfer to real-world fairness-sensitive tasks.

Large-scale image-text datasets, such as LAION-5B, are foundational to modern AI systems, yet their vast scale and uncurated nature raise significant concerns about demographic and stereotypical biases. This study presents a comprehensive analysis of the demographic composition and representational, stereotypical, and intersectional biases in LAION-2B-en and LAION-2B-multi, the two main components of the LAION-5B dataset. Using state-of-the-art models -- FairFace, DeepFace, and Emo-AffectNet -- we analyze faces detected in the dataset to identify biases across age, gender, race, and expressed emotion. Our findings reveal substantial overrepresentation of young adults (20--39), White individuals, and males, alongside consistent underrepresentation of minority racial groups and middle-aged or older women across both dataset components. We also observe stereotypical associations between demographic attributes and emotions, such as Anger'' being predominantly linked to males and Happiness'' to females, pointing to systemic imbalances in the data. The consistency of these patterns across two demographic models and both components of LAION-5B demonstrates that these biases are deeply embedded in one of the most widely-used training datasets. Given the scale at which LAION-5B is used to train generative models, these demographic imbalances could shape the behavior and outputs of numerous downstream AI systems.

Warning: This paper studies stereotypes and biases, and contains potentially disturbing examples, used for illustration purposes only. Our findings should not be interpreted as an argument against alignment. Instead, this paper highlights the need for principled approaches to more advanced alignment. Alignment aims to ensure that large language models (LLMs) behave safely and reliably, including by avoiding unsafe inferences. However, we show that such safety-oriented behaviors can misfire: models may reject warranted conclusions even when they are explicitly supported by context. We call this failure mode misfired alignment, where alignment-induced changes cause LLMs to override explicit evidence. To quantify this phenomenon, specifically on stereotype-related alignment, we introduce VETO, a benchmark consisting of 2,032 BBQ-derived contrastive pairs, and define a new metric, Misfired Alignment Rate (MAR), which measures on a 0 to 100 scale how often a model fails on a stereotype-related question but succeeds on its contrastive counterpart. We benchmark 25 LLMs on VETO, and show that all LLMs, including the most recent ones, exhibit non-trivial (4.7 to 18.9%) MARs while all human participants achieve 0.0% MAR. Controlled priming experiments further show that alignment-induced cues can substantially amplify MAR across LLMs, indicating that these failures are not merely artifacts of individual examples but can be induced by safety-related framing. Mechanistic analyses on open-weight LLMs reveal late-layer suppression of evidence-supported answers, and comparisons between instruct and base LLMs suggest that this suppression emerges after instruction training. These findings show that current alignment methods can overgeneralize surface-level safety cues, to the point of overriding objective evidence, motivating more work on alignment objectives that better preserve contextual grounding.

Socio-cultural stereotypical bias is an important consideration in the development and deployment of NLP systems. It is however often considered only at the national level, despite rich subnational socio-cultural structures. We present AmchiBias, the first benchmark for measuring socio-cultural stereotypical bias for the Indian state of Goa with its unique historically multicultural setting. It covers various Goan identity groups and comprises 313 minimal pairs across eight sociodemographic dimensions in both English and Devanagari Konkani. We then evaluate stereotypical bias in five multilingual encoder models on this benchmark. We find near-chance scores in Konkani, reflecting language incompetence for general multilingual models and a lack of Goan cultural competence for Indian language models. Queried in English, models with a stronger Indian language coverage show higher bias for pan-Indian groups than hyperlocal Goan groups. This suggests the English signal reflects pan-Indian pretraining associations rather than genuine Goan cultural knowledge. Our findings highlight a critical gap in low-resource multilingual NLP evaluation for hyperlocal community identities.

The global use of artificial intelligence has increased interest in assessing the ability to generate culturally localized content, including stories. Cultural localization in stories often occurs through either templated localization -- the use of cultural markers (e.g., names, locations) in a generic narrative -- or holistic localization -- the variation of plots, values, and themes, in addition to cultural markers. We propose a method to measure the degree to which content was generated through templated localization. Specifically, we identify the lexical tokens that distinguish stories across nationalities and measure the similarity of the narratives that remain after removing them. In stories generated by five models on 125 topics for 193 nationalities, our method is able to detect that only a small subset (9-17%) of the vocabulary accounts for the variation across nationalities and that the narratives that remain after removing them contain repeated multi-word sequences, suggesting the presence of a shared culturally-agnostic narrative template. Finally, we characterize the cultural markers for their stereotypicality and offensiveness, finding that markers from 19 countries, mostly located in the Global South, are on average offensive.

Gender bias in AI-generated stories is a well-documented problem. While much attention has been paid to reducing or mitigating this bias, it is not always clear whether interventions produce genuinely fairer results. To investigate this issue, we examine how large language models (LLMs) handle gender assignment in a narrative context that is popular, highly ambiguous, and also known to closely reproduce human stereotypes: stories about talking animals. We prompt six leading LLMs to complete an English-language story about seven different anthropomorphic animal characters whose gender is unstated. We additionally iterate with four different narrative settings and a range of model temperatures. Across the 23.8K stories, we find that models frequently avoid gendering the animal character in the story (19% on average) or use gender-neutral language like "it" or "its" (38.2% on average). However, when gender is assigned, there is a significant masculine bias. Feminine animal characters are virtually absent, present in just 2.2% of stories vs. 40.6% that feature masculine characters. Our findings point to a broader argument: neutrality bites. In other words, models that prioritize neutrality to address social bias may actually contribute to the erasure of marginalized perspectives and identities. We suggest that alternative strategies beyond neutrality need to be pursued, such as ones that more equally distribute social possibilities across imagined subjects.

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.

We audit six large language models (LLMs) for gender stereotyping across English, Korean, Chinese, and Japanese. Three were developed primarily for English-language use (Claude, GPT, Gemini) and three for East Asian use (DeepSeek, Syn-Pro, HyperCLOVA X). We adopt the HEXACO-100 personality inventory and anchor each model against a cross-cultural human dataset spanning 48 countries to ask not whether LLMs are biased, but how far their gender attributions drift from the populations they are deployed among. Our findings show that their stereotyping spans a range roughly 2.5 times wider than the entire cross-country range found in humans, and the effect can compound across languages. One English-centric model, prompted in Korean, reached 5 times the local baseline, even when the prompt stated the candidate had already been hired, which often dampens human stereotyping. To characterize such behaviors without ranking them, we introduce a four-pattern framework -- concordance, suppression, reorganization, and amplification -- across 24 (model x language) cells. Item-level analysis reveals that translation does not just rescale stereotypes, but changes the attributes tied to it, hiding significant rearrangement under the surface while appearing well-calibrated. Our results ultimately suggest that no single debiasing pipeline is likely to address bias evenly across linguistic boundaries.

Third-person singular pronouns have long been used to study stereotypical biases in language models and to test their abilities to reason about reference. More recently, the interplay between reasoning and bias has been investigated with the task of pronoun fidelity, which assesses models' abilities to correctly reuse a previously-specified pronoun for a discourse entity, independent of other potentially distracting discourse entities mentioned in between. However, such research focuses on English, which is a language with limited grammatical gender and almost no gender agreement. In this paper we contribute a novel, large-scale dataset, GRUFF, to measure pronoun fidelity in German, covering four different gender agreement systems in nouns, and four sets of pronouns. With this dataset, we show that LLMs show strong grammatical agreement for masculine and feminine entities in the absence of explicit context, but not for neopronouns xier and en. Models are generally not robust to distractors, but encoder-only models are more robust in German than in English, reflecting the importance of grammatical gender. Finally, we show that occupational stereotypes in this context are poorly correlated across grammatical cases, and across most models, except ones with closely related architectures. We release all code and data to encourage further work on gender-inclusive language and referential reasoning in German.

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.

Hate speech and misinformation frequently co-occur online, amplifying prejudice and polarization. Given their scale, using Large Language Models (LLMs) to assist expert counterspeech (CS) writing has gained interest, yet prior work has addressed these phenomena separately. We bridge this gap by studying CS generation in contexts where both hate and misinformation co-occur. We test three knowledge-driven generation strategies: first we prompt an LLM with fact-checkers' guidelines and fact-checking articles; secondly, with NGOs' guidelines and reports; thirdly, we create a mixed strategy that combines guidelines and documents from both. 23 experts revise the generated CS, which are assessed via human and automatic metrics. While LLMs produce adequate CS in 40% of cases, expert edits substantially improve naturalness, exhaustiveness, and adherence to guidelines. Based on the post-edited CS, the mixed strategy proves to be the most effective in crowdsourcing evaluation, pairing strong factual correction with stereotype mitigation and empathetic engagement. We release a dataset of hateful and misinformed claims with expert-verified CS and supporting knowledge.

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.

Although the cultural (mis)alignment of Large Language Models (LLMs) has attracted increasing attention -- often framed in terms of cultural bias -- until recently there has been limited work on the design and development of datasets for cultural assessment. Here, we review existing approaches to such datasets and identify their main limitations. To address these issues, we propose design guidelines for annotators and report on the construction of a dataset built according to these principles. We further present a series of contrastive experiments conducted with this dataset. The results demonstrate that our design yields test sets with greater discriminative power, effectively distinguishing between models specialized for a given culture and those that are not, ceteris paribus.

Large Language Models (LLMs) are increasingly deployed in socially sensitive settings, raising concerns about fairness and biases, particularly across intersectional demographic attributes. In this paper, we systematically evaluate intersectional fairness in six LLMs using ambiguous and disambiguated contexts from two benchmark datasets. We assess LLM behavior using bias scores, subgroup fairness metrics, accuracy, and consistency through multi-run analysis across contexts and negative and non-negative question polarities. Our results show that while modern LLMs generally perform well in ambiguous contexts, this limits the informativeness of fairness metrics due to sparse non-unknown predictions. In disambiguated contexts, LLM accuracy is influenced by stereotype alignment, with models being more accurate when the correct answer reinforces a stereotype than when it contradicts it. This pattern is especially pronounced in race-gender intersections, where directional bias toward stereotypes is stronger. Subgroup fairness metrics further indicate that, despite low observed disparity in some cases, outcome distributions remain uneven across intersectional groups. Across repeated runs, responses also vary in consistency, including stereotype-aligned responses. Overall, our findings show that apparent model competence is partly associated with stereotype-consistent cues, and no evaluated LLM achieves consistently reliable or fair behavior across intersectional settings. These findings highlight the need for evaluation beyond accuracy, emphasizing the importance of combining bias, subgroup fairness, and consistency metrics across intersectional groups, contexts, and repeated runs.

The rapid adoption of large vision-language models (LVLMs) in recent years has been accompanied by growing fairness concerns due to their propensity to reinforce harmful societal stereotypes. While significant attention has been paid to such fairness concerns in the context of social biases, relatively little prior work has examined the presence of stereotypes in LVLMs related to cultural contexts such as religion, nationality, and socioeconomic status. In this work, we aim to narrow this gap by investigating how cultural contexts depicted in images influence the judgments LVLMs make about a person's moral, ethical, and political values. We conduct a multi-dimensional analysis of such value judgments in nine LVLMs using counterfactual image sets, which depict the same person across different cultural contexts. Our evaluation framework pairs descriptive analyses (Moral Foundations Theory categorization, lexical analyses, and value sensitivity) with a novel grounding analysis that compares LVLM cross-context variation against two large-scale human surveys (MFQ-2 and WVS Wave 7). Across 4.8 million LVLM generations, we identify three bias patterns that replicate across architecturally diverse models: an inversion of the socioeconomic-status-to-Authority relationship found in WVS, and two race-conditional failures that override cultural context cues when depicting Middle Eastern persons. Additional ablations show that the socioeconomic-status-to-Authority inversion bias is amplified by image conditioning and persists across different model sizes.

While recent safety guardrails effectively suppress overtly biased outputs, subtler forms of social bias emerge during complex logical reasoning tasks that evade current evaluation benchmarks. To fill this gap, we introduce a new evaluation framework, PRIME (Puzzle Reasoning for Implicit Biases in Model Evaluation), that uses logic grid puzzles to systematically probe the influence of social stereotypes on logical reasoning and decision making in LLMs. Our use of logic puzzles enables automatic generation and verification, as well as variability in complexity and biased settings. PRIME includes stereotypical, anti-stereotypical, and neutral puzzle variants generated from a shared puzzle structure, allowing for controlled and fine-grained comparisons. We evaluate multiple model families across puzzle sizes and test the effectiveness of prompt-based mitigation strategies. Focusing our experiments on gender stereotypes, our findings highlight that models consistently reason more accurately when solutions align with stereotypical associations. This demonstrates the significance of PRIME for diagnosing and quantifying social biases perpetuated in the deductive reasoning of LLMs, where fairness is critical.

The high memory demands of generative language models have drawn attention to quantization, which reduces memory usage by mapping model weights to lower-precision integers. However, recent empirical studies show that, while efficient, quantization can increase the likelihood of generating biased outputs and degrade performance on fairness benchmarks. In this work, we draw new links between quantization and model fairness by adding explicit group-fairness constraints to the quantization objective and introduce Fair-GPTQ, the first quantization method explicitly designed to reduce unfairness in large language models. The added constraints guide the learning of the rounding operation toward less-biased text generation for protected groups. Specifically, we focus on stereotype generation involving occupational bias and discriminatory language spanning gender, race, and religion. Fair-GPTQ has minimal impact on performance, preserving at least 90% of baseline accuracy on zero-shot benchmarks, reduces unfairness relative to a half-precision model, and retains the memory and speed benefits of 4-bit quantization.

Understanding biases and stereotypes encoded in the weights of Large Language Models (LLMs) is crucial for developing effective mitigation strategies. However, biased behavior is often subtle and non-trivial to isolate, even when deliberately elicited, making systematic analysis and debiasing particularly challenging. To address this, we introduce a simple, cost-effective, and generalizable framework \texttt{BiasGym} for reliably injecting, analyzing, and mitigating conceptual associations of biases within LLMs. \texttt{BiasGym} consists of two modules: \texttt{Inject}, which injects specific biases into the model via token-based fine-tuning while keeping the model frozen, followed by two debiasing methods that leverage these injected signals to identify and reliably suppress (\texttt{Scope}) or \texttt{Steer} the components responsible for biased behavior. Our framework enables consistent bias elicitation for better localization of bias conceptual association in the model space, supports targeted debiasing without degrading performance on downstream tasks, and generalizes to biases unseen during fine-tuning. We demonstrate the effectiveness of our proposed framework in reducing real-world stereotypes (e.g., people from Italy being `reckless drivers'), showing its utility for both safety interventions and interpretability research.

Diffusion-based text-to-image models are increasingly used for urban analysis and scenario generation, but their geographic knowledge and representational biases remain poorly understood. We evaluate FLUX 1-schnell and Stable Diffusion 3.5-Large in the United States by generating 150 street-view images for each state, each state capital, and a generic "USA" prompt. Images are embedded with DINO-v2 ViT-S/14 and compared with Fréchet Inception Distance (FID). Pairwise FID clustering shows that geographically proximate states and capitals often group together, indicating implicit geographic structure. However, the generic ``USA'' prompt collapses this diversity into a metropolitan stereotype: frontier, desert, tropical, rural, and small-city environments are underrepresented or distant in FID space. These results show that diffusion models can encode fine-grained geography while still reproducing narrow national-scale visual stereotypes.

Despite growing empirical evidence of bias amplification in machine learning, its theoretical foundations remain poorly understood. We develop a formal framework for majority-minority learning tasks, showing how standard training can favor majority groups and produce stereotypical predictors that neglect minority-specific features. Assuming population and variance imbalance, our analysis reveals three key findings: (i) the close proximity between ``full-data'' and stereotypical predictors, (ii) the dominance of a region where training the entire model tends to merely learn the majority traits, and (iii) a lower bound on the additional training required. Our results are illustrated through experiments in deep learning for tabular and image classification tasks.

The social biases and unwelcome stereotypes revealed by pretrained language models are becoming obstacles to their application. Compared to numerous debiasing methods targeting word level, there has been relatively less attention on biases present at phrase level, limiting the performance of debiasing in discipline domains. In this paper, we propose an automatic multi-token debiasing pipeline called \textbf{General Phrase Debiaser}, which is capable of mitigating phrase-level biases in masked language models. Specifically, our method consists of a \textit{phrase filter stage} that generates stereotypical phrases from Wikipedia pages as well as a \textit{model debias stage} that can debias models at the multi-token level to tackle bias challenges on phrases. The latter searches for prompts that trigger model's bias, and then uses them for debiasing. State-of-the-art results on standard datasets and metrics show that our approach can significantly reduce gender biases on both career and multiple disciplines, across models with varying parameter sizes.