LLM Bias Detection and Mitigation through the Lens of Desired Distributions

• URL: http://arxiv.org/abs/2510.06354v1
• Date: Tue, 07 Oct 2025 18:20:03 GMT
• Title: LLM Bias Detection and Mitigation through the Lens of Desired Distributions
• Abstract summary: We propose a weighted adaptive loss based fine-tuning method to align gender-profession output with desired distribution.<n>We achieve near-complete mitigation under equality and 30-75% reduction under real-world settings.
• Score: 8.710551702283391
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Although prior work on bias mitigation has focused on promoting social equality and demographic parity, less attention has been given to aligning LLM's outputs to desired distributions. For example, we might want to align a model with real-world distributions to support factual grounding. Thus, we define bias as deviation from a desired distribution, which may be an equal or real-world distribution, depending on application goals. We propose a weighted adaptive loss based fine-tuning method that aligns LLM's gender-profession output distribution with the desired distribution, while preserving language modeling capability. Using 3 profession sets -- male-dominated, female-dominated, and gender-balanced -- derived from U.S. labor statistics (2024), we assess both our adaptive method for reflecting reality and a non-adaptive variant for equality. Across three masked language models, bias is observed under both distributions. We achieve near-complete mitigation under equality and 30-75% reduction under real-world settings. Autoregressive LLMs show no bias under equality but notable bias under real-world settings, with the Llama Instruct models (3.2-3B, 3.1-8B) achieving a 50-62% reduction.

Related papers

• Controlling Distributional Bias in Multi-Round LLM Generation via KL-Optimized Fine-Tuning [37.39836347901149]
  We assess whether Large Language Models (LLMs) can generate outputs that adhere to a desired target distribution.<n>We formulate distribution alignment using the attributes of gender, race, and sentiment within occupational contexts.<n>We propose a novel fine-tuning framework that couples Steering Token with Semantic Alignment.
  arXiv  Detail & Related papers  (2026-04-07T11:58:16Z)
• Evidence-based Distributional Alignment for Large Language Models [58.65469623911573]
  We propose Evi-DA, an evidence-based alignment technique that improves the fidelity and robustness of LLM-based distribution estimation.<n>Given a target country, Evi-DA retrieves related World Values Survey items and their answer distributions, predicts a coarse Welzel value signature for each option, and infers the country-conditioned answer distribution in a structured format.
  arXiv  Detail & Related papers  (2026-03-03T03:34:06Z)
• Judging with Confidence: Calibrating Autoraters to Preference Distributions [56.17041629492863]
  We argue that a reliable autorater must learn to model the full distribution of preferences defined by a target population.<n>We present two learning methods tailored to different data conditions.<n>Our results show that finetuning autoraters with a distribution-matching objective leads to verbalized probability predictions that are better aligned with the target preference distribution.
  arXiv  Detail & Related papers  (2025-09-30T20:36:41Z)
• On Optimal Steering to Achieve Exact Fairness [29.589891801235083]
  Empirically, our optimal steering techniques on both synthetic and real-world datasets improve fairness without diminishing utility.<n>We demonstrate affine steering of LLM representations to reduce bias in multi-class classification.
  arXiv  Detail & Related papers  (2025-09-19T08:37:51Z)
• Different Bias Under Different Criteria: Assessing Bias in LLMs with a Fact-Based Approach [7.969162168078149]
  Large language models (LLMs) often reflect real-world biases, leading to efforts to mitigate these effects. We introduce a novel metric to assess bias using fact-based criteria and real-world statistics.
  arXiv  Detail & Related papers  (2024-11-26T11:32:43Z)
• 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)
• GenderCARE: A Comprehensive Framework for Assessing and Reducing Gender Bias in Large Language Models [73.23743278545321]
  Large language models (LLMs) have exhibited remarkable capabilities in natural language generation, but have also been observed to magnify societal biases.<n>GenderCARE is a comprehensive framework that encompasses innovative Criteria, bias Assessment, Reduction techniques, and Evaluation metrics.
  arXiv  Detail & Related papers  (2024-08-22T15:35:46Z)
• 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)
• GenderBias-\emph{VL}: Benchmarking Gender Bias in Vision Language Models via Counterfactual Probing [72.0343083866144]
  This paper introduces the GenderBias-emphVL benchmark to evaluate occupation-related gender bias in Large Vision-Language Models. Using our benchmark, we extensively evaluate 15 commonly used open-source LVLMs and state-of-the-art commercial APIs. Our findings reveal widespread gender biases in existing LVLMs.
  arXiv  Detail & Related papers  (2024-06-30T05:55:15Z)
• Domain Adaptation meets Individual Fairness. And they get along [48.95808607591299]
  We show that algorithmic fairness interventions can help machine learning models overcome distribution shifts. In particular, we show that enforcing suitable notions of individual fairness (IF) can improve the out-of-distribution accuracy of ML models.
  arXiv  Detail & Related papers  (2022-05-01T16:19:55Z)
• Unimodal-Concentrated Loss: Fully Adaptive Label Distribution Learning for Ordinal Regression [32.35098925000738]
  We argue that existing ALDL algorithms do not fully exploit the intrinsic properties of ordinal regression. We propose a novel loss function for fully adaptive label distribution learning, namely unimodal-concentrated loss.
  arXiv  Detail & Related papers  (2022-04-01T09:40:11Z)

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.