Language Model Debiasing

Follow this topic Ask about this topic

Latest papers

25 papers4 papers in the last four weeks, up 33% on the four weeks before. 0.0% of all new papers.

Oct 15, 2026

Bias Mitigation in Audio-Enabled LLMs through Adversarial Training and Distillation Methods

Audio-enabled large language models (AuLLMs) allow users to interact with them simply by talking to them, without the need for an intermediate transcription. This expands the model's accessibility and capabilities by encoding non-verbal cues. However, using non-verbal cues may lead to biased behaviour based on the attributes inferred (or assumed) from them. In this work, we focus on the gender attribute and show that models' perception of it can be unlearned using adversarial methods without a loss in performance on other benchmarked tasks. Such models are useful in situations where gender inference is unwanted. However, in other practical settings, gender perception (without bias) may be desired.As a less radical measure, we distil the gender-agnostic model, creating a model that perceives gender but responds similarly to the gender-agnostic teacher, unless explicitly asked.We apply our newly proposed methods to three AuLLMs and obtain satisfactory results in the gender-unlearning part and partially satisfactory results in the distilling part.

Adnan Al Ali, Jindřich Libovický, Anne Lauscher

Charles University, Faculty of Mathematics and Physics, Czech Republic · Trustworthy AI Lab, University of Hamburg, Germany

Adversarial Debiasing Language Model Debiasing Gender Bias in Language Models Audio-Language Models LLM Unlearning Adversarial Training+1

Oct 6, 2026

Latent space bias directions in LLMs capture confidence, not fairness

Activation steering has gained popularity as a lightweight inference-time debiasing technique for large language models. However, prior work reports that steering vectors generalise poorly, with unintended effects on model performance and limited transfer to new datasets. Our work analyses what the debiasing direction used for activation steering actually encodes, in order to shed light on its inconsistent performance. We study the linear debiasing direction obtained by contrasting the activations of anti-biased and biased prompts, and evaluate it as a steering intervention across bias and general knowledge benchmarks. We find that this direction is dominated by model confidence, pointing from regions of high to low-probability tokens in activation space rather than encoding a meaningful representation of model bias. Steering along it does reduce measured bias, but this is a consequence of reducing model confidence: on QA benchmarks we find that this steering drives the model to abstain from answering, with a side effect of improving fairness metrics. Our experiments show that model confidence is the dominant separating factor between biased and anti-biased prompts in hidden space, indicating that isolating a linear representation of bias which is disentangled from model confidence is difficult and steering-based debiasing results should be interpreted with care. In short, steering appears to reduce bias, not by correcting the model's underlying preferences, but by making it less confident, even on tasks unrelated to bias.

Stephanie Buttigieg, Maeve Madigan, Parameswaran Kamalaruban +1

Institute of Astronomy & Kavli Institute for Cosmology, University of Cambridge, UK · Risk and Security AI Lab, Visa Inc., Cambridge, UK

Debiased ML Language Model Steering Social Bias in Language Models LLM Interpretability Language Model Debiasing

Oct 1, 2026

Acmite: Mitigating Gender Bias in LLMs through Concept-Guided Mutual Information

Large language models (LLMs) can reproduce social stereotypes from their training data, motivating extensive research on model debiasing. However, existing methods often rely on explicit biased examples or predefined group-term substitutions, making them sensitive to wording and less effective at capturing stereotype concepts shared across diverse contexts. More importantly, they typically suppress biased outputs without explicitly modeling the statistical dependence between model outputs and the underlying stereotype concepts. We propose Acmite, a lightweight concept-guided framework for targeted and selective debiasing. Acmite represents stereotypes as structured semantic concepts and uses maximal marginal relevance (MMR) to select diverse concepts for debiasing. Inspired by mutual information minimization, it approximates this dependence with token-level KL divergence while preserving task semantics. A lightweight LoRA adapter is trained with the base model frozen and activated at inference time only when the input is sufficiently similar to stereotype-related concepts; otherwise, the original model is used directly. We evaluate Acmite on BBQ, CrowS-Pairs, and StereoSet, and assess general capability preservation on ARC-Challenge, GSM8K, and PIQA. Experiments across three LLMs show that Acmite effectively mitigates gender bias across complementary evaluation formats while maintaining competitive performance on bias-unrelated tasks. Anonymous code and data are available at https://anonymous.4open.science/r/Acmite-18E2/.

Tian Lan, Xiaoqing Cheng, Han Zhang +1

Kyoto University · Zhejiang University · Shanghai Jiao Tong University +1

Gender Bias in Language Models Debiased ML Social Bias in Language Models Language Model Debiasing

Sep 30, 2026

Debias It Yourself: Teaching LLMs Cognitive Bias Mitigation Interventions

Bias has long been studied in social psychology and cognitive science, where decades of research have produced a body of validated interventions that reduce stereotypical thinking and prejudiced responses in humans. We propose Debias It Yourself (DIY), a cognitively grounded framework that translates five such interventions into debiasing procedures for large language models and delivers them through three established paradigms: Show (in-context examples), Train (instruction tuning), and Revise (guided self-revision). Across three models, five bias benchmarks, eleven debiasing baselines, and three reasoning benchmarks, Train+Revise and Revise alone attain the top two average ranks, lead the bias-reasoning tradeoff (mean bias as low as 2% at 90% reasoning accuracy), and reduce bias on unseen dimensions by up to 14.8%. Our code and data are publicly available.

Chahat Raj, Sina Mansouri, Aylin Caliskan +2

George Mason University · University of Washington

Cognitive Bias in Language Models Language Model Debiasing Social Bias in Language Models Language Model Bias Evaluation

Sep 18, 2026

FairLMs: A Turnkey Library for Fairness in Language Models

Fairness research on language models involves measuring bias, applying mitigation methods, and examining the evidence on which an evaluation rests. Existing tools offer complementary functionality through different interfaces, so combining them requires reconciling model interfaces, evidence formats, access constraints, and result types before applicability can be checked or methods compared. We introduce FairLMs, a Python library that connects these activities through explicit declarations of model capabilities and input requirements. It provides 33 intrinsic and extrinsic metrics, 14 mitigation components spanning four intervention categories, 14 dataset and scoring-instrument diagnostics, adapters for the three Transformer architectures and supported hosted completion APIs, and benchmark loaders. Declarations are checked before execution and results carry the configuration under which they were obtained, so that compatible components can be combined, methods compared under a common protocol, and workflows extended to new models and datasets. The source code is available at: https://github.com/FairLMs/FairLMs.

Jiale Zhang, Michael Larionov, Zichong Wang +2

Department of Biostatistics and Health Data Science Indiana University Indianapolis, IN, United States · Department of Statistics and Data Science Carnegie Mellon University Pittsburgh, PA, United States · Knight Foundation School of Computing and Information Sciences Florida International University Miami, FL, United States

Language Model Bias Evaluation Social Bias in Language Models Language Model Debiasing

Sep 7, 2026

The Illusion of Debiasing: Persona Steering Redistributes Rather Than Reduces Bias in LLMs

Prompt-based interventions: system prompts, personas, role instructions, reliably reshape what a language model says, but it is unclear which layer they reach. Do they reconfigure internal structure, or only modulate the output channel? We use persona conditioning as a controlled probe, measuring its effects along a depth axis from self-report, through open-ended generation, to word-level parametric association, across three instruction-tuned models. We find a graded dissociation. Personas are legible but not structural: models follow single-trait instructions yet fail to reproduce human inter-trait covariance. The dissociation deepens with depth: personas hold or amplify closed-form QA bias, shift absolute tone while leaving between-group disparity unchanged, and barely perturb an already saturated associative baseline. Prompt-based steering thus operates in the output channel and has a structural reach limit that surface manipulability can mask.

Ziyue Feng, Hongbo Fang, James A. Evans

University of Chicago Chicago, IL, USA

Language Model Steering Language Model Debiasing Persona Prompting Social Bias in Language Models Language Model Bias Evaluation

Aug 30, 2026

CoCoA: Context-Conditional Cultural Alignment for Large Language Models

Large Language Models (LLMs) often favor Western-associated entities across cultural contexts. Conventional debiasing methods aim for uniform neutrality, but cultural bias mitigation demands context-conditional behavior, preferring culturally appropriate entities when cultural cues are present and remaining neutral when they are absent. We propose CoCoA (Context-Conditional Cultural Alignment), a framework that learns this behavior through dual-context training on the same entity pairs under contexts with and without cultural cues. CoCoA combines a contrastive alignment objective with calibration and drift regularization, optimized through goal-aware gradient reconciliation. We evaluate CoCoA on CAMeL and Camellia, two entity-centric cultural bias benchmarks, across ten language settings and four LLMs. CoCoA reduces the Cultural Bias Score from 43 to 24 on average while maintaining near-neutral preferences at 50.2, with minimal impact on general performance across five standard benchmarks. These findings highlight that effective cultural alignment requires context-conditional modeling rather than uniform debiasing, and establish a new direction for mitigating entity-centric cultural bias in LLMs.

Kyungdon Lee, Wei Xu, Alan Ritter +2

Sungkyunkwan University, Suwon, South Korea · Georgia Institute of Technology, GA, USA · University of Southern California, CA, USA

Cultural Bias in Language Models Language Model Debiasing Cultural Alignment LLM Alignment Cross-Cultural Language Model Evaluation

Aug 26, 2026

Adaptive Triggering for Bias Correction in LLM Reasoning

Chain-of-thought prompting can expose and amplify demographic stereotypes within an LLM's intermediate reasoning and create a failure mode that final-answer debiasing alone cannot address. Mitigating such bias during generation presents a fundamental timing problem: intervening too late allows biased reasoning to propagate, while unnecessarily intervening can disrupt otherwise correct reasoning. Existing approaches largely avoid this decision by either evaluating completed reasoning chains post hoc or intervening at predetermined steps, leaving open when a developing reasoning trajectory provides sufficient evidence to warrant correction. We formulate this decision as an online change-point detection problem. A per-step bias signal updates a CUSUM statistic and a targeted correction is injected only when accumulated evidence crosses a detector-specific threshold calibrated on held-out data. We instantiate the framework with a white-box signal derived from next-token probabilities and a black-box signal obtained from an LLM judge, enabling deployment with both open-weight and hosted models. On gpt-4o-mini adaptive black-box triggering recovers most of the disambiguated-context accuracy lost under fixed-interval intervention while requiring substantially fewer interventions. That result holds even with an independent judge. Across six open-weight models, the white-box signal improves ambiguous-item accuracy on all six but reduces disambiguated-item accuracy on five because it cannot distinguish unsupported stereotype reliance from correct, stereotype-congruent evidence.

Nayoung Kim, Mickey Mancenido, Huan Liu

School of Computing and Augmented Intelligence, Arizona State University, Tempe, AZ, USA · School of Mathematical and Natural Sciences, Arizona State University, Phoenix, AZ, USA

Language Model Debiasing Demographic Bias in Language Models CoT Reasoning Language Model Bias Evaluation

Aug 1, 2026

A Heuristic Perspective on Debiasing Language Models

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

Tian Lan, Yemin Wang, Chuancheng Shi +6

Inner Mongolia University · Xiamen University · University of Sydney +3

Social Bias in Language Models Language Model Debiasing Cultural Bias in Language Models Linguistic Bias in Language Models

Jun 30, 2026

Wait, am I Being Fair? Characterizing Deductive Stereotyping and Mitigating It with Fair-GCG

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.

Naihao Deng, Yilun Zhu, Joan Nwatu +2

University of Michigan

Language Model Steering Social Bias in Language Models Language Model Debiasing

Jun 10, 2026

Debiasing Without Protected Attributes: Latent Concept Erasure from Textual Profiles

Most fairness research in NLP assumes direct access to protected attributes such as gender, race, or nationality. In practice, however, such information is often unavailable due to privacy constraints, missing metadata, or legal restrictions, even though models may infer it from indirect textual cues. This raises a key question: can debiasing succeed without direct access to sensitive attributes? We propose H-SAL, which performs post-hoc concept and attribute erasure using self-description text as an implicit debiasing signal. To support this setting, we introduce a multi-domain Stack Exchange-based fairness benchmark for helpfulness prediction that includes both explicit and implicit signals, enabling comparison between standard debiasing with protected labels and debiasing without access to sensitive information. Across encoder and decoder-only language models, we find that implicit self-description often matches or outperforms explicit-label-based debiasing. Our results broaden representation-level fairness research and provide a new benchmark for studying debiasing under realistic data constraints.

Shun Shao, Zheng Zhao, Anna Korhonen +2

University of Cambridge · University of Edinburgh · University of Groningen +1

Debiased ML Algorithmic Fairness Representation Disentanglement Demographic Bias in Language Models Concept Erasure Language Model Debiasing

May 28, 2026

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 Conformal Prediction for Language Models Language Model Bias Evaluation Linguistic Bias in Language Models Language Model Debiasing

May 23, 2026

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 Dialect Bias in Language Models Language Model Bias Evaluation Linguistic Bias in Language Models Language Model Debiasing

May 15, 2026

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 Language Model Debiasing

May 4, 2026

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)

Social Bias in Language Models Language Model Decoding Process Reward Models Debiased ML Linguistic Bias in Language Models Language Model Bias Evaluation+1

Apr 25, 2026

Judging the Judges: A Systematic Evaluation of Bias Mitigation Strategies in LLM-as-a-Judge Pipelines

LLM-as-a-Judge has become the dominant paradigm for evaluating language model outputs, yet LLM judges exhibit systematic biases that compromise evaluation reliability. We present a comprehensive empirical study comparing nine debiasing strategies across five judge models from four provider families (Google, Anthropic, OpenAI, Meta), three benchmarks (MT-Bench n=400, LLMBar n=200, custom n=375), and four bias types. Our headline practical finding is that a mid-tier model with the right debiasing can outperform frontier judges at a fraction of the cost: Gemini 2.5 Flash with the Combined Budget strategy reaches the highest agreement of any configuration we tested (71.0%, kappa=0.549) at ~

0.001 per evaluation, about 15x cheaper than the best frontier setup (Claude Sonnet 4, 69.5%, ~

0.015). Other key findings: (1) Style bias is the dominant bias (0.10-0.76 across models, favoring markdown over plain prose), far exceeding position bias (<=0.04), yet is rarely studied. (2) Verbosity bias is heterogeneous when measured length-aware: Pro, Flash, and Llama prefer longer answers (+0.24 to +0.44), Claude prefers concise (-0.12), and GPT-4o is neutral (-0.04); on truncation controls all models correctly prefer the complete response (0.88-1.00 accuracy). (3) Debiasing helps multiple models: Claude S8 (+11.5 pp), Flash S8 (+7.5 pp), and Claude S5 (+7.3 pp) survive Holm-Bonferroni correction, with Flash S1 (+4.7 pp) and Llama S8 (+4.5 pp) also significant. We release our evaluation framework, the 375-pair controlled dataset, and per-instance cached results for all nine strategies.

Sadman Kabir Soumik

Independent Researcher

Debiased ML LLM-as-a-Judge Language Model Generation Evaluation Language Model Bias Evaluation Bias in LLM-as-a-Judge Language Model Debiasing

Apr 23, 2026

When Bigger Isn't Better: A Comprehensive Fairness Evaluation of Political Bias in Multi-News Summarisation

Multi-document news summarisation systems are increasingly adopted for their convenience in processing vast daily news content, making fairness across diverse political perspectives critical. However, these systems can exhibit political bias through unequal representation of viewpoints, disproportionate emphasis on certain perspectives, and systematic underrepresentation of minority voices. This study presents a comprehensive evaluation of such bias in multi-document news summarisation using FairNews, a dataset of complete news articles with political orientation labels, examining how large language models (LLMs) handle sources with varying political leanings across 13 models and five fairness metrics. We investigate both baseline model performance and effectiveness of various debiasing interventions, including prompt-based and judge-based approaches. Our findings challenge the assumption that larger models yield fairer outputs, as mid-sized variants consistently outperform their larger counterparts, offering the best balance of fairness and efficiency. Prompt-based debiasing proves highly model dependent, while entity sentiment emerges as the most stubborn fairness dimension, resisting all intervention strategies tested. These results demonstrate that fairness in multi-document news summarisation requires multi-dimensional evaluation frameworks and targeted, architecture-aware debiasing rather than simply scaling up.

Nannan Huang, Iffat Maab, Junichi Yamagishi

RMIT University, Australia · National Institute of Informatics, Tokyo, Japan

Social Bias in Language Models Language Model Debiasing Political Bias in Language Models Text Summarization Language Model Bias Evaluation

Mar 28, 2026

Debiasing Large Language Models toward Social Factors in Online Behavior Analytics through Prompt Knowledge Tuning

Attribution theory explains how individuals interpret and attribute others' behavior in a social context by employing personal (dispositional) and impersonal (situational) causality. Large Language Models (LLMs), trained on human-generated corpora, may implicitly mimic this social attribution process in social contexts. However, the extent to which LLMs utilize these causal attributions in their reasoning remains underexplored. Although using reasoning paradigms, such as Chain-of-Thought (CoT), has shown promising results in various tasks, ignoring social attribution in reasoning could lead to biased responses by LLMs in social contexts. In this study, we investigate the impact of incorporating a user's goal as knowledge to infer dispositional causality and message context to infer situational causality on LLM performance. To this end, we introduce a scalable method to mitigate such biases by enriching the instruction prompts for LLMs with two prompt aids using social-attribution knowledge, based on the context and goal of a social media message. This method improves the model performance while reducing the social-attribution bias of the LLM in the reasoning on zero-shot classification tasks for behavior analytics applications. We empirically show the benefits of our method across two tasks-intent detection and theme detection on social media in the disaster domain-when considering the variability of disaster types and multiple languages of social media. Our experiments highlight the biases of three open-source LLMs: Llama3, Mistral, and Gemma, toward social attribution, and show the effectiveness of our mitigation strategies.

Hossein Salemi, Jitin Krishnan, Hemant Purohit

George Mason University, Fairfax, Virginia, United States

Language Model Debiasing Social Bias in Language Models Causal Reasoning in Language Models Social Media Analysis Intent Classification

Mar 23, 2026

CatRAG: Functor-Guided Structural Debiasing with Retrieval Augmentation for Fair LLMs

Large Language Models (LLMs) are deployed in high-stakes settings but can show demographic, gender, and geographic biases that undermine fairness and trust. Prior debiasing methods, including embedding-space projections, prompt-based steering, and causal interventions, often act at a single stage of the pipeline, resulting in incomplete mitigation and brittle utility trade-offs under distribution shifts. We propose CatRAG Debiasing, a dual-pronged framework that integrates functor with Retrieval-Augmented Generation (RAG) guided structural debiasing. The functor component leverages category-theoretic structure to induce a principled, structure-preserving projection that suppresses bias-associated directions in the embedding space while retaining task-relevant semantics. On the Bias Benchmark for Question Answering (BBQ) across three open-source LLMs (Meta Llama-3, OpenAI GPT-OSS, and Google Gemma-3), CatRAG achieves state-of-the-art results, improving accuracy by up to 40% over the corresponding base models and by more than 10% over prior debiasing methods, while reducing bias scores to near zero (from 60% for the base models) across gender, nationality, race, and intersectional subgroups.

Ravi Ranjan, Utkarsh Grover, Mayur Akewar +2

Florida International University Miami, USA · University of South Florida Tampa, USA

Language Model Debiasing Social Bias in Language Models Algorithmic Bias Demographic Bias in Language Models Language Model Bias Evaluation

Mar 19, 2026

UGID: Unified Graph Isomorphism for Debiasing Large Language Models

Large language models (LLMs) exhibit pronounced social biases. Output-level or data-optimization--based debiasing methods cannot fully resolve these biases, and many prior works have shown that biases are embedded in internal representations. We propose Unified Graph Isomorphism for Debiasing large language models (UGID), an internal-representation--level debiasing framework for large language models that models the Transformer as a structured computational graph, where attention mechanisms define the routing edges of the graph and hidden states define the graph nodes. Specifically, debiasing is formulated as enforcing invariance of the graph structure across counterfactual inputs, with differences allowed only on sensitive attributes. UGID jointly constrains attention routing and hidden representations in bias-sensitive regions, effectively preventing bias migration across architectural components. To achieve effective behavioral alignment without degrading general capabilities, we introduce a log-space constraint on sensitive logits and a selective anchor-based objective to preserve definitional semantics. Extensive experiments on large language models demonstrate that UGID effectively reduces bias under both in-distribution and out-of-distribution settings, significantly reduces internal structural discrepancies, and preserves model safety and utility.

Zikang Ding, Junchi Yao, Junhao Li +4

University of Electronic Science and Technology of China, Chengdu, China · Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates · South China University of Technology, Guangzhou, China

Language Model Debiasing Social Bias in Language Models Demographic Bias in Language Models

Mar 14, 2026

Preconditioned Test-Time Adaptation for Out-of-Distribution Debiasing in Narrative Generation

Although debiased large language models (LLMs) excel at handling known or low-bias prompts, they often fail on unfamiliar and high-bias prompts. We demonstrate via out-of-distribution (OOD) detection that these high-bias prompts cause a distribution shift, degrading static model performance. To enable real-time correction, we propose CAP-TTA, a test-time adaptation framework. CAP-TTA triggers context-aware LoRA updates only when a bias-risk score exceeds a set threshold. By utilizing an offline precomputed diagonal preconditioner, it ensures fast and stable optimization. Across multiple benchmarks and human evaluations, CAP-TTA effectively reduces toxicity/bias score with significantly lower latency than standard optimization methods (e.g., AdamW or SGD). Furthermore, it prevents catastrophic forgetting, and substantially improves narrative fluency over state-of-the-art baselines without compromising debiasing performance.

Hanwen Shen, Ting Ying, Jiajie Lu +1

Laboratory for Artificial Intelligence in Mathematics Education, Stevens Institute of Technology · Independent Researcher · NLP2CT Lab, Department of Computer and Information Science, University of Macau

Narrative Generation Language Model Debiasing Inference-Time Adaptation of Language Models Social Bias in Language Models Text Generation

Mar 9, 2026

Toward Robust LLM-Based Judges: Taxonomic Bias Evaluation and Debiasing Optimization

Large language model (LLM)-based judges are widely adopted for automated evaluation and reward modeling, yet their judgments are often affected by judgment biases. Accurately evaluating these biases is essential for ensuring the reliability of LLM-based judges. However, existing studies typically investigate limited biases under a single judge formulation, either generative or discriminative, lacking a comprehensive evaluation. To bridge this gap, we propose JudgeBiasBench, a benchmark for systematically quantifying biases in LLM-based judges. JudgeBiasBench defines a taxonomy of judgment biases across 4 dimensions, and constructs bias-augmented evaluation instances through a controlled bias injection pipeline, covering 12 representative bias types. We conduct extensive experiments across both generative and discriminative judges, revealing that current judges exhibit significant and diverse bias patterns that often compromise the reliability of automated evaluation. To mitigate judgment bias, we propose bias-aware training that explicitly incorporates bias-related attributes into the training process, encouraging judges to disentangle task-relevant quality from bias-correlated cues. By adopting reinforcement learning for generative judges and contrastive learning for discriminative judges, our methods effectively reduce judgment biases while largely preserving general evaluation capability.

Hongli Zhou, Hui Huang, Rui Zhang +5

Faculty of Computing, Harbin Institute of Technology, Harbin, 150001, China · School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, 518055, China

LLM-as-a-Judge Social Bias in Language Models Language Model Debiasing Language Model Bias Evaluation Bias in LLM-as-a-Judge Automated Evaluation

Jan 29, 2026

Knowing Bias, Doing Better: Mitigating Social Bias in LLMs via Know-Bias Neuron Enhancement

Large language models (LLMs) exhibit social biases that reinforce harmful stereotypes, limiting their safe deployment. Most existing debiasing methods adopt a suppressive paradigm by modifying parameters, prompts, or neurons associated with biased behavior; however, such approaches are often brittle, weakly generalizable, data-inefficient, and prone to degrading general capability. We propose KnowBias, a lightweight and conceptually distinct framework that mitigates bias by strengthening, rather than suppressing, neurons encoding bias-knowledge. KnowBias identifies neurons encoding bias knowledge using a small set of bias-knowledge questions via attribution-based analysis, and selectively enhances them at inference time. This design enables strong debiasing while preserving general capabilities, generalizes across bias types and demographics, and is highly data efficient, requiring only a handful of simple yes/no questions and no retraining. Experiments across multiple benchmarks and LLMs demonstrate consistent state-of-the-art debiasing performance with minimal utility degradation. Data and code are available at https://github.com/JP-25/KnowBias.

Jinhao Pan, Chahat Raj, Anjishnu Mukherjee +4

Department of Computer Science, George Mason University, Fairfax, VA, USA · Lightridge High School, Aldie, VA, USA

Debiased ML Social Bias in Language Models Language Model Debiasing Demographic Bias in Language Models Activation Steering

Aug 12, 2025

BiasGym: A Simple and Generalizable Framework for Analyzing and Removing Biases through Injection

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 BiasGym for reliably injecting, analyzing, and mitigating conceptual associations of biases within LLMs. BiasGym consists of two modules: 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 (Scope) or 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.

Sekh Mainul Islam, Nadav Borenstein, Siddhesh Milind Pawar +3

University of Copenhagen

Social Bias in Language Models LLM Interpretability Language Model Debiasing Language Model Bias Evaluation

Nov 23, 2023

General Phrase Debiaser: Debiasing Masked Language Models at a Multi-Token Level

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 General Phrase Debiaser, which is capable of mitigating phrase-level biases in masked language models. Specifically, our method consists of a phrase filter stage that generates stereotypical phrases from Wikipedia pages as well as a 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.

Bingkang Shi, Xiaodan Zhang, Dehan Kong +4

Chinese Academy of Sciences, Institute of Information Engineering, Beijing 100093, China · Alibaba Group, Alibaba Artificial Intelligence Governance Laboratory, Beijing, China · University of Bristol, Department of Electrical and Electronic Engineering, Bristol, BS8 1UB, UK

Gender Bias in Language Models Debiased ML Masked Language Modeling Social Bias in Language Models Linguistic Bias in Language Models Language Model Debiasing