paper-with-me

Papers

Evaluating and Mitigating Social Bias for Large Language Models in Open-ended Settings

2024-12-09 · Zhao Liu, Tian Xie, Xueru Zhang

Current social bias benchmarks for Large Language Models (LLMs) primarily rely on pre-defined question formats like multiple-choice, limiting their ability to reflect the complexity and open-ended nature of real-world interactions. To address this gap, we extend an existing BBQ dataset introduced by incorporating fill-in-the-blank and short-answer question types, designed to evaluate biases in an open-ended setting. Our finding reveals that LLMs tend to produce responses that are more biased against certain protected attributes, like age and socio-economic status. On the other hand, these biased outputs produced by LLMs can serve as valuable contexts and chains of thought for debiasing. Our debiasing approach combined zero-shot, few-shot, and chain-of-thought could significantly reduce the level of bias to almost 0. We open-source our evaluation and debiasing code hoping to encourage further measurements and mitigation of bias and stereotype in LLMs.

📄 PDF Abstract BibTeX arXiv:2412.06134

Code (1)

zhaoliu0914/LLM-Bias-Benchmark 공식 구현

Tasks

Multiple-choice

Similar Papers 제목 키워드 기반

On Evaluating and Mitigating Gender Biases in Multilingual Settings

2023-07-04 · Aniket Vashishtha, Kabir Ahuja, Sunayana Sitaram

While understanding and removing gender biases in language models has been a long-standing problem in Natural Language Processing, prior research work has primarily been limited to English. In this work, we investigate s…

My Answer Is NOT 'Fair': Mitigating Social Bias in Vision-Language Models via Fair and Biased Residuals

2025-05-26 · Jian Lan, Yifei Fu, Udo Schlegel, Gengyuan Zhang 외

Social bias is a critical issue in large vision-language models (VLMs), where fairness- and ethics-related problems harm certain groups of people in society. It is unknown to what extent VLMs yield social bias in generat…

EthicsFairnessMultiple-choice

Social Bias Evaluation for Large Language Models Requires Prompt Variations

2024-07-03 · Rem Hida, Masahiro Kaneko, Naoaki Okazaki

Warning: This paper contains examples of stereotypes and biases. Large Language Models (LLMs) exhibit considerable social biases, and various studies have tried to evaluate and mitigate these biases accurately. Previous …

Sensitivity

A Group Fairness Lens for Large Language Models

2023-12-24 · Guanqun Bi, Lei Shen, Yuqiang Xie, Yanan Cao 외

The rapid advancement of large language models has revolutionized various applications but also raised crucial concerns about their potential to perpetuate biases and unfairness when deployed in social media contexts. Ev…

AttributeFairnessText Generation

LFTF: Locating First and Then Fine-Tuning for Mitigating Gender Bias in Large Language Models

2025-05-21 · Zhanyue Qin, Yue Ding, Deyuan Liu, Qingbin Liu 외

Nowadays, Large Language Models (LLMs) have attracted widespread attention due to their powerful performance. However, due to the unavoidable exposure to socially biased data during training, LLMs tend to exhibit social …