paper-with-me

홈 › Papers

A Heuristic Perspective on Debiasing Language Models

2026-08-01 · Tian Lan, Yemin Wang, Chuancheng Shi, Xiangyu Wu, Zesheng Shi, Yuan Wang, Jiang Li, Guanglai Gao, Xiangdong Su arxiv

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.

📄 PDF Abstract BibTeX arXiv:2608.00622

Code (0)

등록된 구현이 없습니다.

Tasks

Natural Language Understanding

Similar Papers 제목 키워드 기반

Self-Debias: Self-correcting for Debiasing Large Language Models

2026-04-09 · Xuan Feng, Shuai Zhao, Luwei Xiao, Tianlong Gu 외 arxiv

Although Large Language Models (LLMs) demonstrate remarkable reasoning capabilities, inherent social biases often cascade throughout the Chain-of-Thought (CoT) process, leading to continuous "Bias Propagation". Existing …

Large Language Model Bias Mitigation from the Perspective of Knowledge Editing

2024-05-15 · Ruizhe Chen, Yichen Li, Zikai Xiao, Zuozhu Liu

Existing debiasing methods inevitably make unreasonable or undesired predictions as they are designated and evaluated to achieve parity across different social groups but leave aside individual facts, resulting in modifi…

Fairnessknowledge editingLanguage ModelingLanguage Modelling+2

Leveraging Pre-trained Language Models for Gender Debiasing

2022-06-01 · LREC 2022 6 · Nishtha Jain, Declan Groves, Lucia Specia, Maja Popović

Studying and mitigating gender and other biases in natural language have become important areas of research from both algorithmic and data perspectives. This paper explores the idea of reducing gender bias in a language …

Text Generation

Pitfalls of Conversational LLMs on News Debiasing

2024-04-09 · Ipek Baris Schlicht, Defne Altiok, Maryanne Taouk, Lucie Flek

This paper addresses debiasing in news editing and evaluates the effectiveness of conversational Large Language Models in this task. We designed an evaluation checklist tailored to news editors' perspectives, obtained ge…

Misinformation

Reducing Spurious Correlations for Answer Selection by Feature Decorrelation and Language Debiasing

2022-10-01 · COLING 2022 10 · Zeyi Zhong, Min Yang, Ruifeng Xu

Deep neural models have become the mainstream in answer selection, yielding state-of-the-art performance. However, these models tend to rely on spurious correlations between prediction labels and input features, which in…

Answer SelectionContrastive Learning