Debiasing

Follow this topic Ask about this topic

Momentum

1 paper in the last four weeks, down 67% on the four weeks before. 0.0% of all new papers.

Jul 6Week of Sep 21

Latest papers 24

Oct 1, 2026cs.LG

Debias Anything: Fairness with Diversity without Supervision in Diffusion Models

Although diffusion models produce high-quality images, they also reproduce and amplify demographic imbalances in their training data. Debiasing their generation process post-training w.r.t. some sensitive attribute usually relies on classifier guidance or explicit text extra-conditioning, but this reduces methods' applicability and output diversity. Conversely, methods promoting diversity alone do not ensure fair attribute representation. In this paper, we propose a method tackling fairness and diversity jointly that is generally applicable to any diffusion model and any sensitive attribute. To this end, an adapter connects the frozen diffusion model to a pretrained vision-language embedding space, enabling fairness and diversity guidance without sensitive-attribute annotations. For fairness, pairs of text prompts define attribute directions which guide batch composition towards specific proportions. For diversity, we introduce a score measuring disagreement between the semantic estimates derived from this representation. The formulation supports unconditional and text-conditional diffusion models, while requiring no prior knowledge or data of sensitive attribute. Experiments confirm that our method improves quality and diversity scores at comparable fairness levels.

Théau d'Audiffret, Mariia Vladimirova, Jean-Yves Franceschi

Criteo AI Lab, Paris, France · ESSEC Business School, France · CentraleSupélec, Université Paris-Saclay, France +1

Diffusion Models Algorithmic Fairness Diversity Debiasing Disparities

Oct 1, 2026cs.CL

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 Stereotype Mitigation Debiasing Mutual Information

Sep 29, 2026cs.LG

Learning-Enabled Estimation: Tight Characterizations under Sample Selection Biases

When can we learn from biased samples? We study regression when outcomes are observed only after passing through selection filters that depend on both covariates and outcomes themselves, a ubiquitous challenge spanning clinical trials with patient dropout, labor markets with self-selection, and auctions with strategic entry. Ignoring such selection yields systematically biased conclusions with real-world consequences. This challenge has a long history in econometrics and statistics, starting with Heckman's seminal two-stage model and followed by numerous generalizations. While these works provide various sufficient conditions for identification, a complete characterization of when such regression is possible has remained elusive. In this work, we provide a characterization for when regression is possible in the presence of sample selection bias. Our results establish the minimal assumptions required on the functional forms of selection processes under which regression remains possible, which are particularly relevant in modern settings where selection mechanisms are increasingly complex and opaque. As a corollary of our characterization, we show that there are settings where the regression function can be identified even when the selection filter itself cannot. This observation already goes beyond the ``estimate selection filter, then debias regression'' paradigm that is followed by virtually all existing approaches. Under natural strengthenings of our identification conditions, we also establish finite-sample estimation guarantees with explicit convergence rates and provide oracle-efficient algorithms. This yields the first general-purpose estimation method for this broad class of selection problems. Finally, we explore the implications of our results for several well-studied econometric settings with complex selection mechanisms such as auctions with entry costs and labor markets.

Vikram Kher, Jane H. Lee, Anay Mehrotra +1

Yale University · Stanford University

Selection Bias Finite-Sample Debiasing

Sep 29, 2026cs.CV

OFBD: Object-Focused Background Debiasing for Long-Tailed Learning

Balancing performance trade-offs on long-tailed data distributions remains a long-standing challenge in visual recognition. Existing methods mainly improve tail classes through re-balancing, representation learning, or data augmentation, but the underlying cause of tail class degradation is still insufficiently explored. In this paper, we find that standard long-tailed training induces background-biased representation and optimization: tail classes suffer larger background distribution shifts and become increasingly driven by background gradients. This reveals that tail degradation is not merely caused by insufficient samples, but also by the learning of irrelevant background features. To tackle this issue, we propose Object-Focused Background Debiasing (OFBD), a framework that mitigates background bias from both distribution and optimization perspectives. Specifically, Foreground-guided CutMix preserves target-related foregrounds while diversifying complementary backgrounds, and Background-guided Feature Rectification suppresses background-biased features without learnable parameters or additional training. Extensive experiments show that our method improves overall accuracy, achieves significant tail-class gains, and can serve as a plug-in for mainstream long-tailed methods without external data or pretrained recognition models. The code is available at: https://ofbd-neurips2026-longtail-learning.github.io/

Shenghan Chen, Yiming Liu, Zhipeng Deng +6

Westlake University, Hangzhou, China · Shandong University, Jinan, China · Hokkaido University, Sapporo, Japan +1

Out-Of-Distribution Detection Debiasing Degradation

Aug 31, 2026cs.AI

Authority Bias in Conversational Search Engines for Academic Paper Recommendation

Large Language Models (LLMs) are increasingly used as conversational search engines for academic literature, yet whether they judge papers on content or on authority signals has not been tested causally. We investigate authority bias: systematic preference for papers based on author prestige, venue, and citations rather than content. Holding title and abstract constant, we vary authority metadata across three counterfactual conditions (original, flipped, boosted) over eight LLMs (five open-weight and three frontier closed-weight) in an in-context, single-turn, top-1 recommendation setting. Our experiments show that authority bias is substantial and directional, varies markedly across models, and is only partially addressable through prompt-level debiasing. We further document a say-do gap: debiasing instructions suppress authority mentions far faster than authority-driven flips, so surface auditing systematically underestimates behavioral bias.

Uthman Jinadu, Parsa Ghazvinian, Anjila Budathoki +3

Georgia State University · University of Tennessee, Knoxville

Large Language Model Bias Large Language Model Decisions Debiasing

Aug 12, 2026cs.CV

Localizing to Debias: A Patch-Level Benchmark and Baseline for Weakly Supervised Spatial Anomaly Detection

Despite growing interest in weakly supervised video anomaly detection (WSVAD), current methods struggle to bridge the gap between coarse temporal supervision and fine-grained spatial reasoning. A key obstacle is the tendency of temporal detectors to latch onto background and scene-level cues rather than truly discriminative anomaly evidence. This background bias raises ethical concerns: models may inadvertently associate anomalies with societal or environmental context rather than authentic crime-related cues. Without spatial grounding, such biases remain hidden and unauditable. To address this, we propose SST-WSVADL, a sparse spatio-temporal framework that bridges temporal anomaly detection with fine-grained spatial localization. Rather than processing all spatial regions indiscriminately, SST-WSVADL progressively focuses on the most anomaly-relevant spatio-temporal regions through dynamic sparsification, naturally suppressing background dominant content while preserving discriminative evidence. The temporal and spatial branches are coupled end-to-end via motion-aware regularization that guides sparsification toward dynamically informative regions, without relying on external detectors or vision-language prompts. We publicly release frame-level spatial annotations and a method-agnostic evaluation protocol for three public datasets: UCF-Crime, XD-Violence, and MSAD. These resources enable the community to audit spatial biases in WSVAD predictions, supporting progress toward more ethical and accountable anomaly detection. Experiments demonstrate that SST-WSVADL is competitive with prior methods across benchmarks while enabling localization and patch-level auditability of scene bias, providing a reproducible foundation for interpretability-oriented evaluation of WSVAD models.

Sara Abdulaziz, Abdulrahman Al-Abri, Giacomo D'Amicantonio +1

Eindhoven University of Technology, 5612 AE Eindhoven, Netherlands

Training-Free Video Anomaly Detection Spatial Supervision Spatial Grounding Debiasing

Aug 11, 2026cs.CV

Towards Color-Faithful Low-Light Image Enhancement via Adaptive Color Debiasing and Saturation Rectification

Low-light imaging often introduces color bias caused by the low signal-to-noise ratio and the image formation process. Although recent low-light image enhancement methods have achieved strong brightness recovery, faithful color restoration remains challenging, manifesting as overall color bias together with local under- and over-saturation. To address this issue, we propose CAGE, a cylindrical color correction framework with adaptive color debiasing and gamut-harmonized saturation rectification for color-faithful low-light image enhancement. We first introduce AdaLAB, a cylindrical adaptive LAB color space that provides a decoupled and image-specific basis for uniform color correction. Building on this color space, we further develop AdaCCT, an adaptive cylindrical color transform with forward and inverse transforms for the conversion between RGB and AdaLAB color space, as well as necessary color debiasing and saturation rectification. The forward transform suppresses embedded color bias before backbone enhancement by reorganizing the chromatic distribution through chromatic-plane shifting and scaling, while the inverse transform achieves faithful saturation rectification through out-of-gamut lightness compensation. Extensive experiments on multiple benchmarks show that CAGE achieves more faithful color restoration, specifically reduces color bias and saturation abnormality, and delivers better overall visual quality across different low-light enhancement backbones. The code is available at https://yangzhichen763.github.io/CAGE/.

Zhichen Yang, Rui Xu, Yuzhen Niu +3

Fuzhou University, Fuzhou, Fujian, China

Low-Light Image Enhancement Enhancement Saturation Debiasing

Aug 7, 2026cs.CV

Debias in Text, Believe Your Eyes: Text-Anchored Cross-Modal Transfer for Visual Counter-Commonsense Reasoning

The visual reasoning ability of multimodal large language models (MLLMs) is crucial for downstream applications, particularly counter-commonsense reasoning, which requires models to reason beyond common assumptions. Recent studies mainly improve visual counter-commonsense reasoning by enhancing visual inputs, following the assumption that failures originate from insufficient visual grounding. However, our empirical analysis reveals that the bottleneck is not visual perception. MLLMs already capture the relevant visual evidence, and the correct answer exists in their decoding space. Instead, the shared language decoder resolves prior--evidence conflicts by favoring dominant language priors, especially for low-frequency factual scenarios. Motivated by this, we first propose a text-anchored data construction pipeline, whose core component, Fact-Frequency Distillation (FFD), estimates the prior strength of commonsense facts and distills verified counter-commonsense scenarios into a high-quality text corpus. Building upon this corpus, we introduce TACT, a text-anchored post-training framework that debiases the shared language decoder without requiring any visual training data. TACT routes evidence-following and prior-driven reasoning trajectories into different optimization stages, enabling the decoder to resolve prior--evidence conflicts. Across counter-commonsense visual benchmarks, TACT substantially improves visual reasoning while preserving general capabilities, demonstrating effective text-to-vision cross-modal transfer.

Chen Ling, Hanqian Li, Dongnan Liu +9

Zhejiang University · Ant Group · The Hong Kong University of Science and Technology (Guangzhou) +2

Multimodal Large Language Models Visual Evidence Reasoning Skills Debiasing Text Analysis and Detection

Aug 1, 2026cs.CL

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

Large Language Model Bias Debiasing Heuristics

Jul 24, 2026cs.IR

PinEqualizer: Full Funnel Content Exploration and Debiasing System at Pinterest

In this paper, we propose a new solution for addressing the content cold-start problem in industry-scale search and recommender systems. Compared to prior approaches, we have made the following new contributions: 1) our solution spans the entire multi-stage funnel and generalizes well for both search and recommendation surfaces, 2) our solution reduces bias favoring existing content, allowing more accurate model prediction across content types and reducing short-term tradeoffs associated with high volumes of explicit content exploration, 3) our solution is evaluated with a scalable measurement framework that enables fast short-term experimentation while validating long-term impact. We have iteratively built and successfully deployed this new system at Pinterest in the past two years and observed significant improvements in fresh content exploration, overall user engagement, and content ecosystem health.

Olafur Gudmundsson, Bo Zhao, Huayi Liao +15

Pinterest, Inc. San Francisco, USA

Jun 23, 2026cs.CV

Dual-Branch Cross-Projection Debiasing through Diffusion-based Disentanglement

Foundation models trained on biased datasets often rely on spurious correlations between target labels and non-causal attributes, resulting in poor generalization on minority groups. Bias mitigation remains challenging due to two fundamental issues. First, when group labels are unavailable, existing group-unsupervised methods typically infer spurious attributes implicitly from model behavior, making it difficult to identify spurious factors that are semantically aligned with real-world biases. Second, even with pseudo spurious supervision, most existing debiasing methods follow a single-branch design that operates within a single shared feature space, where target and spurious attributes are intrinsically entangled. To address the first challenge, we introduce Confidence-guided Bias Concept Mining (CBCM), which leverages diffusion-disentangled, semantically grounded concept representations to identify reliable spurious attributes without attribute annotations. To address the second challenge, we propose Dual-branch Cross-projection Debiasing (DCD), a prompt-tuning framework that separates target and spurious representations into two branches and explicitly removes spurious information through cross null-space projection while preserving target-relevant semantics. Extensive experiments on four benchmark datasets show that our method achieves state-of-the-art worst group accuracy among group-unsupervised approaches, while tuning at most 0.22% of the model parameters. The source code is available in the supplementary materials.

Xiangqian Zhao, Xinyang Jiang, Zhipeng Xu +5

Xidian University · Shaanxi, China · Microsoft Research Asia +1

Debiasing Unsupervised

Jun 22, 2026cs.CY

Uncertainty-based Debiasing and Unlearning for Decontamination

Benchmark-based evaluation is the dominant paradigm for assessing large language model (LLM) capabilities, yet data contamination inflates reported performance and undermines fair comparison. Existing decontamination methods are evaluated solely through aggregate accuracy, which can obscure substantial differences in per-sample model behaviour, and many require access to an uncontaminated model. In this paper, we propose a sample-level evaluation framework for decontamination that complements accuracy-based assessment with distributional distance metrics, measuring how closely a decontaminated model recovers the output distribution of an uncontaminated model on each sample. Building on this framework, we introduce Uncertainty-Based Decontamination (UBD), a family of methods that leverage deep ensembles of the contaminated model to estimate per-sample memorization without requiring a uncontaminated model or knowledge of which samples are contaminated. UBD estimates a per-sample correction scalar from ensemble uncertainty, which is used to construct a debiased target distribution that suppresses the inflated probability mass on correct answers induced by contamination. This target is then used either as a post-hoc output correction (debiasing) or as a soft training signal for parameter update (unlearning). Experiments on MMLU-Pro and MATH-MCQA across multiple LLM backbones demonstrate that UBD produces per-sample output distributions substantially closer to those of an uncontaminated model than paraphrasing or choice-permutation baselines, while preserving model performance on uncontaminated data.

Guangzhi Sun, Xiao Zhan, Mark Gales

Department of Engineering, University of Cambridge · VRAIN, Universitat Politècnica de València

Large Language Model Unlearning Debiasing Multi-Dimensional Evaluation Post-Hoc

Jun 10, 2026cs.CL

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

Debiasing Large Language Model Bias Algorithmic Fairness Natural Language Processing Concept Erasure Profile

Jun 6, 2026cs.CL

What Does Debiasing Really Remove? A Geometric Study of PCA-Based Gender Debiasing in Word Embeddings

Debiasing methods based on principal component analysis (PCA) are broadly used to reduce gender bias in word embeddings used in LLMs, yet it remains unclear what aspects of bias they actually remove and how destructive this process is. These methods are based on the understanding that bias resides in a low-dimensional subspace, with the assumption that most of it can be captured by a few principal components. In this work, we conduct a systematic geometric analysis of PCA-based gender debiasing and investigate what is actually removed from the embedding space. Our experiments across multiple embeddings show that direct gender bias is primarily concentrated in the first principal component, supporting the low-rank bias hypothesis. However, associative bias measured by WEAT does not align with these principal directions and is instead spread across multiple embedding dimensions. Furthermore, as expected, we demonstrate that removing an increasing number of principal components leads to a consistent degradation of the embedding geometry, affecting semantic structure and vector relationships. These results reveal that PCA-based debiasing operates as a trade-off: while it effectively reduces certain forms of direct bias, it fails to eliminate distributed associations and introduces geometric distortion. Moreover, there is no universal optimal level of debiasing, as the balance between bias reduction and semantic preservation depends on the chosen metric and embedding. Overall, our findings suggest that bias in word embeddings is not purely low-rank and that simple subspace removal methods may be insufficient for comprehensive debiasing.

Alexey Kresin, Tchifou M. Dieffi, Tomer Caspi

Department of Computer Science, Hood College, Frederick, MD, United States · Department of Mathematics, Ben-Gurion University of the Negev, Be'er Sheva, Israel

Debiasing Contextual Embeddings Principal Component Analysis Gender Low-Rank Structure

Jun 2, 2026stat.ML

Resource-Constrained Adaptive Inference for Sequential Pricing

Resource-constrained pricing controllers can make fixed-price inference impossible: the controller's resource state may remove the target price neighborhood from the feasible set, even when every realized action has a known positive density. We formalize this support-exclusion failure through a local non-identification result and a realized information clock. We then design a target-aware pricing controller that certifies feasible target bands and logs continuous local densities. Localized debiasing gives studentized intervals whose width is governed by this clock. The resulting regret--information accounting, stated up to pilot re-solving error, shows that cheap exploration can be insufficient for inference: polynomial target mass gives polynomial rates, while a pure

1/t

target branch does not yield shrinking fixed-target intervals without additional local movement. Experiments show calibration in certified bands and diagnostic abstention when the resource state collapses target support.

Ruicheng Ao, Jiashuo Jiang, David Simchi-Levi

Institute for Data, Systems, and Society, Massachusetts Institute of Technology, Cambridge, MA 02139 · Department of Industrial Engineering and Decision Analytics, Hong Kong University of Science and Technology, Hong Kong · Department of Civil and Environmental Engineering and Operations Research Center, Massachusetts Institute of Technology, Cambridge, MA 02139

Dynamic Pricing Exploration Debiasing

May 29, 2026cs.AI

Industrializing Prediction-Powered Inference: The GLIDE Library for Reliable GenAI and Agentic Systems Evaluation

Reliable evaluation of agentic systems requires unbiased estimates with valid uncertainty, but standard practice navigates between costly human annotation and biased LLM-as-judge proxies. Prediction-powered inference (PPI) combines both into debiased estimates with valid confidence intervals, yet its various methods remain scattered across papers under partial implementations. We introduce GLIDE, an open-source Python library that unifies state-of-the-art PPI estimators (PPI++, Stratified PPI, Predict-Then-Debias and its stratified variants, Active Statistical Inference) and samplers (uniform, stratified, active, cost-optimal) under a scipy-style API specialized to mean estimation. GLIDE ships with a reproducible Monte Carlo validation suite, an empirically grounded decision tree for method selection, and an agentic evaluation case study showing substantial annotation savings at equivalent precision. The GLIDE package is available at this URL: https://github.com/EmertonData/glide

Grégoire Martinon, Ibrahim Merad, Mohammed Raki

Emerton Data, 16 Avenue Hoche, 75008, Paris, France.

Agentic Inference Agentic Evaluations Debiasing Industrial Monte Carlo

May 25, 2026cs.CV

Personalized Generative Models for Contextual Debiasing

Different visual patterns appear with different frequencies in the world: e.g., beach balls appear on sand more often than they do on a road. These statistics are reflected in vision datasets, and as a result trained models more easily recognize objects in common scenarios. However, recognizing a beach ball on a road may arguably be even more important than recognizing it on sand. We study how to mitigate this discrepancy. Since collecting uncommon images in the real world may be difficult, we explore whether generating images with less frequent contexts can serve as effective training augmentation. A key challenge is guiding generations to remain close to the original dataset distribution while creating diverse images with uncommon contexts. We introduce Decoupling Contextual Patterns with Generations (DecoupleGen), a method that personalizes text-to-image diffusion models to facilitate coherent synthesis of images with rare contexts while preserving original visual details. The generated images contain semantically meaningful content and remain visually aligned with the original datasets. We further apply verification constraints to ensure relevance of the augmented data. We evaluate our approach on object classification and recognition tasks on complex scene datasets. Our experiments demonstrate consistent improvements over previous approaches, and our analyses identify factors underlying these improvements.

Xinran Liang, Esin Tureci, Prachi Sinha +3

Department of Computer Science, Princeton University · LIX, CNRS, ´Ecole Polytechnique

Data Augmentation Generative Models Vision Datasets Debiasing

May 25, 2026stat.ME

Geometry Adaptive Counterfactual Distribution Learning with Diffusion-Guided Smoothing

We study counterfactual distribution learning for high-dimensional outcomes whose counterfactual law may concentrate near lower-dimensional structure. Standard isotropic smoothing treats all ambient directions equally, leading to unfavorable scaling and unstable local inference. We propose two diffusion-guided estimators based on semiparametric debiasing: diffusion-informed smoothing for counterfactual densities and diffusion-informed score smoothing for counterfactual scores. The estimators combine causal nuisance adjustment with geometry-adaptive localization driven by diffusion score information, removing first-order nuisance bias while aligning smoothing with local outcome geometry. We establish asymptotic expansions, risk bounds, and inference procedures for smoothed density and score-based targets, with ambient density inference obtained under additional approximation conditions. Under structural geometry conditions, the leading stochastic error is governed by an effective dimension induced by the diffusion-guided kernel, rather than by the ambient dimension. Semi-synthetic experiments based on CelebA show steeper error decay for geometry-adaptive methods, supporting the proposed effective-dimension theory.

Kwangho Kim

Department of Statistics, Korea University

Causal Inferences Distributions Low-Dimensional Structure Debiasing

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

Large Language Model Bias Debiasing Biases Reranking

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)

Large Language Model Bias Debiasing Decoding Process Reward Model Multilingual Benchmark Model Weights

May 1, 2026cs.CL

Can AI Debias the News? LLM Interventions Improve Cross-Partisan Receptivity but LLMs Overestimate Their Own Effectiveness

Partisan news media erode cross-partisan trust, but large language models (LLMs) offer a potential means of debiasing such content at scale. Across two pre-registered experiments, we tested whether LLM-generated debiasing of liberal news headlines could improve conservative readers' trust-relevant judgments. Study 1 found that subtle lexical debiasing (replacing emotive words with more moderate synonyms) had no effect on any outcome. Study 2 found that a more substantive reframing intervention significantly increased conservatives' perceived trustworthiness, completeness, and willingness to engage with liberal news headlines, without producing a backfire effect among a sample of liberals. In Study 1, the intervention produced robust effects among LLM-simulated silicon participants, whereas it had no impact on human readers. In Study 2, the intervention's effects among silicon participants aligned directionally with human responses but were significantly larger in magnitude for some outcomes. Moderation analyses revealed that the model's implicit theory of who responds to debiasing diverged from the psychological profile that actually predicted human responsiveness. These findings demonstrate that LLM-based debiasing can improve cross-partisan receptivity when targeting ideological framing rather than surface-level language, but that current models lack both the quantitative accuracy and qualitative psychological fidelity to evaluate their own interventions without human oversight.

Faisal Feroz, Jonas R. Kunst

Department of Experimental Psychology, University of Oxford · Uehiro Oxford Institute, University of Oxford · Psychology Programme, School of Social Sciences, Nanyang Technological University +1

Large Language Model Bias Ideology Debiasing Political Discourse Credibility Headlines+1

Mar 9, 2026cs.CL

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

Judges Debiasing Betting

Jan 29, 2026cs.AI

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 \textbf{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

Large Language Model Bias Debiasing Biases Suppression

Nov 23, 2023cs.CL

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 \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.

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

Debiasing Large Language Model Bias Stereotype Mitigation Language Modeling Linguistics Representation-Level Misalignment