BTBR: A Bayesian-Theory-Driven Probabilistic-Fuzzy Framework for Implicit Bias Removal in Large Language Models

Abstract

-cross Abstract: Large language models (LLMs) may encode biased associations from heterogeneous training corpora that are not immediately visible under ordinary prompting, but can surface when the model is steered toward particular demographic personas. Such behavior often manifests not as explicit toxic output, but as systematic performance differences across semantically equivalent tasks, making the resulting bias difficult to detect and mitigate. To address this issue, we formalize the implicit bias problem as persona-induced performance disparity and argue that bias evidence should be treated as a graded signal rather than a binary label. Motivated by this observation, we model biased knowledge as a fuzzy subset equipped with an explicit membership function that reflects the strength of bias evidence for each candidate example. Building on this formulation, we propose Bayesian-Theory-based Bias Removal (BTBR), a hybrid probabilistic-fuzzy framework for identifying and removing latent bias traces from model parameters. BTBR first performs likelihood-ratio screening to measure how strongly candidate samples align with a target biased persona, then converts high-membership samples into structured knowledge triples, and finally applies targeted model editing with a lightweight fuzzy rule scheduler to reduce collateral performance degradation under high entanglement risk. Extensive experiments across multiple bias sources, tasks, model families and editing backends show that BTBR consistently reduces persona-induced performance gaps while preserving general reasoning ability. These results demonstrate that combining probabilistic evidence with fuzzy degree modeling provides an effective and practical approach for mitigating implicit bias in large language models.

Authors 6

Yongxin Deng (University of Technology Sydney), Xiaoyu Tan (National University of Singapore), Jing Pan (Monash University), Ling Chen (University of Technology Sydney), Zhen Fang (University of Technology Sydney), Xihe Qiu (National University of Singapore)

Specification

Official page

arxiv.org/abs/2408.10608

Source:arXiv (Atom API + RSS)·T1·observed 4 h ago·high

Arxiv announce type

replace

Source:arXiv (Atom API + RSS)·T1·observed 4 h ago·high

arXiv id

2408.10608

Source:arXiv (Atom API + RSS)·T1·observed 4 h ago·high

Categories

cs.CL, cs.AI

Source:arXiv (Atom API + RSS)·T1·observed 4 h ago·high

PDF

arxiv.org/pdf/2408.10608

Source:arXiv (Atom API + RSS)·T1·observed 4 h ago·high

Primary category

cs.CL

Source:arXiv (Atom API + RSS)·T1·observed 4 h ago·high

Published

11 Sept 2026

Source:arXiv (Atom API + RSS)·T1·observed 4 h ago·high

Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →

Provenance