BiasGym is a cost‑effective, generalizable framework that injects specific biases into large language models via token‑based fine‑tuning while keeping the model frozen. It then uses two debiasing methods—Scope and Steer—to identify and suppress or redirect the components responsible for biased behavior. The framework enables consistent bias elicitation, precise localization of bias associations, and targeted debiasing without harming downstream performance, and it has been shown to reduce real‑world stereotypes such as labeling Italians as reckless drivers.
By Sekh Mainul Islam, Nadav Borenstein, Siddhesh Milind Pawar, Haeun Yu, Arnav Arora, Isabelle Augenstein
The paper introduces GPTBIAS, a framework that uses powerful large language models like GPT‑4 to evaluate bias in other LLMs. It employs specially crafted prompts called Bias Attack Instructions to probe for bias and outputs a bias score along with detailed information such as bias types, affected demographics, keywords, reasons, and improvement suggestions. Extensive experiments demonstrate the framework’s effectiveness and usability.
By Jiaxu Zhao, Meng Fang, Shirui Pan, Wenpeng Yin, Mykola Pechenizkiy
arXiv:2408.10608v2 Announce Type: replace
Abstract: Large language models (LLMs) may encode biased associations from heterogeneous training corpora that are not immediately visible under ordinary pro...
By 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)
The paper introduces a unified framework that simultaneously measures intrinsic (encoded) and extrinsic (expressed) gender bias in large language models using identical neutral prompts. It finds a consistent link between latent gender information and output bias, but shows that alignment via supervised fine‑tuning reduces expressed bias while leaving internal gender associations largely intact and reactivatable by adversarial prompts. The study also demonstrates that debiasing gains on structured benchmarks may not transfer to realistic tasks such as story generation.
By Nour Bouchouchi, Thibault Laugel, Xavier Renard, Christophe Marsala, Marie-Jeanne Lesot, Marcin Detyniecki
arXiv:2607. 20073v1 Announce Type: new Abstract: AI-based recruitment systems that rely on machine learning models trained on historical CV data, risk perpetuating and amplifying social biases.
By Farnaz Faramarzi Lighvan, Lynn Houthuys
arXiv:2601. 21864v2 Announce Type: replace Abstract: Large language models (LLMs) exhibit social biases that reinforce harmful stereotypes, limiting their safe deployment.
By Jinhao Pan, Chahat Raj, Anjishnu Mukherjee, Sina Mansouri, Bowen Wei, Shloka Yada, Ziwei Zhu
The paper introduces a bias depth score to differentiate between stable model preferences (Deep biases) and prompt‑dependent responses (Shallow biases) in large language models. By analyzing 4,442 opinion prompts across four models, it finds that only about a quarter of concentrated preferences persist after scenario reframing, indicating that most are shallow. The study shows Deep biases are more often inherited from pretraining and harder to remove through fine‑tuning or prompt‑based debiasing, highlighting the need to distinguish learned biases from prompt artifacts.
By An Vo, Vy Tuong Dang, Khai-Nguyen Nguyen, Emilio Villa-Cueva, Thamar Solorio, Anh Totti Nguyen, Daeyoung Kim
arXiv:2512. 08724v3 Announce Type: replace Abstract: Text-to-image (TTI) diffusion models have achieved remarkable visual quality, yet they have been repeatedly shown to exhibit social biases across sensitive attributes such as gender, race and age.
By Manos Plitsis, Giorgos Bouritsas, Vassilis Katsouros, Yannis Panagakis
arXiv:2502. 11603v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) exhibit strong natural language understanding capabilities but also inherit and amplify societal biases, particularly gender bias, raising fairness concerns.
By Hongye Qiu, Yue Xu, Yi Wang, Meikang Qiu, Wenjie Wang
arXiv:2602. 04306v2 Announce Type: replace-cross Abstract: As large language models (LLMs) are increasingly deployed in real-world applications, ensuring their fair responses across demographics has become crucial.
By Kahee Lim, Soyeon Kim, Steven Euijong Whang
arXiv:2608.29590v1 Announce Type: new
Abstract: We propose a societal bias evaluation method for large vision-language models (LVLMs) in the era of strong safety guardrails. Existing benchmarks rely...
By Yusuke Hirota, Michael Ross Boone, Arun George Zachariah, Jibin Rajan Varghese, Yu-Chiang Frank Wang, Boyi Li, Ryo Hachiuma
Debias‑SparseGPT is a post‑training pruning technique that adds a representational debiasing term based on demographically contrasting inputs to mitigate bias amplification caused by weight sparsification. The method is validated across various generative LLMs and sparsity levels (25%, 50%, and structured 2:4), consistently reducing pruning‑induced bias while maintaining perplexity and zero‑shot accuracy. In the most aggressive 2:4 sparsity regime, enriching the calibration set with long‑context, content‑rich examples further improves both downstream performance and fairness.
By Irina Proskurina, Guillaume Metzler, Antoine Gourru, Julien Velcin