Silenced Biases: The Dark Side LLMs Learned to Refuse

• URL: http://arxiv.org/abs/2511.03369v1
• Date: Wed, 05 Nov 2025 11:24:50 GMT
• Title: Silenced Biases: The Dark Side LLMs Learned to Refuse
• Authors: Rom Himelstein, Amit LeVi, Brit Youngmann, Yaniv Nemcovsky, Avi Mendelson,
• Abstract summary: We introduce the concept of silenced biases, which are unfair preferences encoded within models' latent space.<n>We propose the Silenced Bias Benchmark (SBB), which aims to uncover these biases by employing activation steering.
• Score: 5.2630646053506345
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Safety-aligned large language models (LLMs) are becoming increasingly widespread, especially in sensitive applications where fairness is essential and biased outputs can cause significant harm. However, evaluating the fairness of models is a complex challenge, and approaches that do so typically utilize standard question-answer (QA) styled schemes. Such methods often overlook deeper issues by interpreting the model's refusal responses as positive fairness measurements, which creates a false sense of fairness. In this work, we introduce the concept of silenced biases, which are unfair preferences encoded within models' latent space and are effectively concealed by safety-alignment. Previous approaches that considered similar indirect biases often relied on prompt manipulation or handcrafted implicit queries, which present limited scalability and risk contaminating the evaluation process with additional biases. We propose the Silenced Bias Benchmark (SBB), which aims to uncover these biases by employing activation steering to reduce model refusals during QA. SBB supports easy expansion to new demographic groups and subjects, presenting a fairness evaluation framework that encourages the future development of fair models and tools beyond the masking effects of alignment training. We demonstrate our approach over multiple LLMs, where our findings expose an alarming distinction between models' direct responses and their underlying fairness issues.

Related papers

• Breaking the Benchmark: Revealing LLM Bias via Minimal Contextual Augmentation [12.56588481992456]
  Large Language Models have been shown to demonstrate stereotypical biases in their representations and behavior.<n>We introduce a novel and general augmentation framework that involves three plug-and-play steps.<n>We find that Large Language Models are susceptible to perturbations to their inputs, showcasing a higher likelihood to behave stereotypically.
  arXiv  Detail & Related papers  (2025-10-27T23:05:12Z)
• Adaptive Generation of Bias-Eliciting Questions for LLMs [18.608477560948003]
  Large language models (LLMs) are now widely deployed in user-facing applications, reaching hundreds of millions worldwide.<n>We introduce a counterfactual bias evaluation framework that automatically generates realistic, open-ended questions over sensitive attributes such as sex, race, or religion.<n>We also capture distinct response dimensions that are increasingly relevant in user interactions, such as asymmetric refusals and explicit acknowledgment of bias.
  arXiv  Detail & Related papers  (2025-10-14T13:08:10Z)
• D-REX: A Benchmark for Detecting Deceptive Reasoning in Large Language Models [62.83226685925107]
  Deceptive Reasoning Exposure Suite (D-REX) is a novel dataset designed to evaluate the discrepancy between a model's internal reasoning process and its final output.<n>Each sample in D-REX contains the adversarial system prompt, an end-user's test query, the model's seemingly innocuous response, and, crucially, the model's internal chain-of-thought.<n>We demonstrate that D-REX presents a significant challenge for existing models and safety mechanisms.
  arXiv  Detail & Related papers  (2025-09-22T15:59:40Z)
• Guiding LLM Decision-Making with Fairness Reward Models [12.32062012708603]
  Large language models are increasingly used to support high-stakes decisions.<n>We propose a framework for training a generalizable Fairness Reward Model.<n>We show that our approach consistently improves fairness while matching, or even surpassing, baseline accuracy.
  arXiv  Detail & Related papers  (2025-07-15T14:20:23Z)
• ALBAR: Adversarial Learning approach to mitigate Biases in Action Recognition [52.537021302246664]
  Action recognition models often suffer from background bias (i.e., inferring actions based on background cues) and foreground bias (i.e., relying on subject appearance)<n>We propose ALBAR, a novel adversarial training method that mitigates foreground and background biases without requiring specialized knowledge of the bias attributes.<n>We evaluate our method on established background and foreground bias protocols, setting a new state-of-the-art and strongly improving combined debiasing performance by over 12% absolute on HMDB51.
  arXiv  Detail & Related papers  (2025-01-31T20:47:06Z)
• Explicit vs. Implicit: Investigating Social Bias in Large Language Models through Self-Reflection [18.625071242029936]
  Large Language Models (LLMs) have been shown to exhibit various biases and stereotypes in their generated content.<n>This paper presents a systematic framework to investigate and compare explicit and implicit biases in LLMs.
  arXiv  Detail & Related papers  (2025-01-04T14:08:52Z)
• On the Fairness, Diversity and Reliability of Text-to-Image Generative Models [68.62012304574012]
  multimodal generative models have sparked critical discussions on their reliability, fairness and potential for misuse.<n>We propose an evaluation framework to assess model reliability by analyzing responses to global and local perturbations in the embedding space.<n>Our method lays the groundwork for detecting unreliable, bias-injected models and tracing the provenance of embedded biases.
  arXiv  Detail & Related papers  (2024-11-21T09:46:55Z)
• The Root Shapes the Fruit: On the Persistence of Gender-Exclusive Harms in Aligned Language Models [91.86718720024825]
  We center transgender, nonbinary, and other gender-diverse identities to investigate how alignment procedures interact with pre-existing gender-diverse bias.<n>Our findings reveal that DPO-aligned models are particularly sensitive to supervised finetuning.<n>We conclude with recommendations tailored to DPO and broader alignment practices.
  arXiv  Detail & Related papers  (2024-11-06T06:50:50Z)
• Diverging Preferences: When do Annotators Disagree and do Models Know? [92.24651142187989]
  We develop a taxonomy of disagreement sources spanning 10 categories across four high-level classes. We find that the majority of disagreements are in opposition with standard reward modeling approaches. We develop methods for identifying diverging preferences to mitigate their influence on evaluation and training.
  arXiv  Detail & Related papers  (2024-10-18T17:32:22Z)
• Investigating Implicit Bias in Large Language Models: A Large-Scale Study of Over 50 LLMs [0.0]
  Large Language Models (LLMs) are being adopted across a wide range of tasks. Recent research indicates that LLMs can harbor implicit biases even when they pass explicit bias evaluations. This study highlights that newer or larger language models do not automatically exhibit reduced bias.
  arXiv  Detail & Related papers  (2024-10-13T03:43:18Z)
• Covert Bias: The Severity of Social Views' Unalignment in Language Models Towards Implicit and Explicit Opinion [0.40964539027092917]
  We evaluate the severity of bias toward a view by using a biased model in edge cases of excessive bias scenarios. Our findings reveal a discrepancy in LLM performance in identifying implicit and explicit opinions, with a general tendency of bias toward explicit opinions of opposing stances. The direct, incautious responses of the unaligned models suggest a need for further refinement of decisiveness.
  arXiv  Detail & Related papers  (2024-08-15T15:23:00Z)
• Identifying and Mitigating Social Bias Knowledge in Language Models [52.52955281662332]
  We propose a novel debiasing approach, Fairness Stamp (FAST), which enables fine-grained calibration of individual social biases.<n>FAST surpasses state-of-the-art baselines with superior debiasing performance.<n>This highlights the potential of fine-grained debiasing strategies to achieve fairness in large language models.
  arXiv  Detail & Related papers  (2024-08-07T17:14:58Z)
• Take Care of Your Prompt Bias! Investigating and Mitigating Prompt Bias in Factual Knowledge Extraction [56.17020601803071]
  Recent research shows that pre-trained language models (PLMs) suffer from "prompt bias" in factual knowledge extraction. This paper aims to improve the reliability of existing benchmarks by thoroughly investigating and mitigating prompt bias.
  arXiv  Detail & Related papers  (2024-03-15T02:04:35Z)
• GPTBIAS: A Comprehensive Framework for Evaluating Bias in Large Language Models [83.30078426829627]
  Large language models (LLMs) have gained popularity and are being widely adopted by a large user community. The existing evaluation methods have many constraints, and their results exhibit a limited degree of interpretability. We propose a bias evaluation framework named GPTBIAS that leverages the high performance of LLMs to assess bias in models.
  arXiv  Detail & Related papers  (2023-12-11T12:02:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.