BiasFilter: An Inference-Time Debiasing Framework for Large Language Models

• URL: http://arxiv.org/abs/2505.23829v1
• Date: Wed, 28 May 2025 08:09:10 GMT
• Title: BiasFilter: An Inference-Time Debiasing Framework for Large Language Models
• Authors: Xiaoqing Cheng, Ruizhe Chen, Hongying Zan, Yuxiang Jia, Min Peng,
• Abstract summary: Mitigating social bias in large language models (LLMs) has become an increasingly important research objective.<n>This paper proposes BiasFilter, a model-agnostic, inference-time debiasing framework that integrates seamlessly with both open-source and API-based LLMs.
• Score: 7.549501011153965
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Mitigating social bias in large language models (LLMs) has become an increasingly important research objective. However, existing debiasing methods often incur high human and computational costs, exhibit limited effectiveness, and struggle to scale to larger models and open-ended generation tasks. To address these limitations, this paper proposes BiasFilter, a model-agnostic, inference-time debiasing framework that integrates seamlessly with both open-source and API-based LLMs. Instead of relying on retraining with balanced data or modifying model parameters, BiasFilter enforces fairness by filtering generation outputs in real time. Specifically, it periodically evaluates intermediate outputs every few tokens, maintains an active set of candidate continuations, and incrementally completes generation by discarding low-reward segments based on a fairness reward signal. To support this process, we construct a fairness preference dataset and train an implicit reward model to assess token-level fairness in generated responses. Extensive experiments demonstrate that BiasFilter effectively mitigates social bias across a range of LLMs while preserving overall generation quality.

Related papers

• Evaluating and Mitigating Social Bias for Large Language Models in Open-ended Settings [13.686732204665738]
  We extend an existing BBQ dataset by incorporating fill-in-the-blank and short-answer question types.<n>Our finding reveals that LLMs produce responses that are more biased against certain protected attributes, like age and socio-economic status.<n>Our debiasing approach combined zero-shot, few-shot, and chain-of-thought could significantly reduce the level of bias to almost 0.
  arXiv  Detail & Related papers  (2024-12-09T01:29:47Z)
• Towards Resource Efficient and Interpretable Bias Mitigation in Large Language Models [1.787433808079955]
  Large language models (LLMs) have been observed to perpetuate unwanted biases in training data.<n>In this paper, we mitigate bias by leveraging small biased and anti-biased expert models to obtain a debiasing signal.<n> Experiments on mitigating gender, race, and religion biases show a reduction in bias on several local and global bias metrics.
  arXiv  Detail & Related papers  (2024-12-02T16:56:08Z)
• Causal-Guided Active Learning for Debiasing Large Language Models [40.853803921563596]
  Current generative large language models (LLMs) may still capture dataset biases and utilize them for generation. Previous prior-knowledge-based debiasing methods and fine-tuning-based debiasing methods may not be suitable for current LLMs. We propose a casual-guided active learning framework, which utilizes LLMs itself to automatically and autonomously identify informative biased samples and induce the bias patterns.
  arXiv  Detail & Related papers  (2024-08-23T09:46:15Z)
• 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)
• BiasDPO: Mitigating Bias in Language Models through Direct Preference Optimization [0.0]
  Large Language Models (LLMs) have become pivotal in advancing natural language processing, yet their potential to perpetuate biases poses significant concerns. This paper introduces a new framework employing Direct Preference Optimization (DPO) to mitigate gender, racial, and religious biases in English text. By developing a loss function that favors less biased over biased completions, our approach cultivates a preference for respectful and non-discriminatory language.
  arXiv  Detail & Related papers  (2024-07-18T22:32:20Z)
• Self-Exploring Language Models: Active Preference Elicitation for Online Alignment [88.56809269990625]
  We propose a bilevel objective optimistically biased towards potentially high-reward responses to actively explore out-of-distribution regions. Our experimental results demonstrate that when fine-tuned on Zephyr-7B-SFT and Llama-3-8B-Instruct models, Self-Exploring Language Models (SELM) significantly boosts the performance on instruction-following benchmarks.
  arXiv  Detail & Related papers  (2024-05-29T17:59:07Z)
• ChatGPT Based Data Augmentation for Improved Parameter-Efficient Debiasing of LLMs [65.9625653425636]
  Large Language models (LLMs) exhibit harmful social biases. This work introduces a novel approach utilizing ChatGPT to generate synthetic training data.
  arXiv  Detail & Related papers  (2024-02-19T01:28:48Z)
• 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)
• Debiasing Vision-Language Models via Biased Prompts [79.04467131711775]
  We propose a general approach for debiasing vision-language foundation models by projecting out biased directions in the text embedding. We show that debiasing only the text embedding with a calibrated projection matrix suffices to yield robust classifiers and fair generative models.
  arXiv  Detail & Related papers  (2023-01-31T20:09:33Z)
• Adversarial Filters of Dataset Biases [96.090959788952]
  Large neural models have demonstrated human-level performance on language and vision benchmarks. Their performance degrades considerably on adversarial or out-of-distribution samples. We propose AFLite, which adversarially filters such dataset biases.
  arXiv  Detail & Related papers  (2020-02-10T21:59:21Z)

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.