The paper "Fairness Definitions in Language Models Explained" surveys and clarifies various fairness notions applicable to language models (LMs). It introduces a taxonomy categorizing these concepts by transformer architecture—encoder-only, decoder-only, and encoder-decoder—and demonstrates each definition through experiments to illustrate practical implications. The authors also discuss current research challenges and open questions to encourage further innovation in the field.
By Zhipeng Yin, Zichong Wang, Avash Palikhe, Wenbin Zhang
arXiv:2606. 30989v1 Announce Type: cross Abstract: Warning: This paper contains several toxic and offensive statements.
By Naihao Deng, Yilun Zhu, Joan Nwatu, Clayton Scott, Rada Mihalcea
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:2509. 16462v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly used in high-stakes decision-making systems, where biased predictions can reinforce social and economic disparities.
By Mina Arzaghi, Alireza Dehghanpour Farashah, Florian Carichon, Jean-Fran\c{c}ois Plante, Golnoosh Farnadi
The paper introduces a novel framework for assessing second‑order bias in large language models (LLMs), defined as bias in how an LLM judges the acceptability of biased content. Using principles from entitlement epistemology, the authors design a reasoning task that asks LLMs to determine whether a biased text is acceptable for specific demographic groups, and propose two metrics to quantify biased judgments. Experiments on both open‑source and closed‑source models reveal that the task bypasses safety guardrails, uncovers systematic variations across target groups, and demonstrates that models still rely on demographic labels when evaluating bias.
By Ramaravind Kommiya Mothilal, Terry Jingchen Zhang, Raiyan Ahmed, Zhijing Jin, Shion Guha, Syed Ishtiaque Ahmed
arXiv:2604.20677v3 Announce Type: replace
Abstract: Large Language Models (LLMs) are increasingly deployed in socially sensitive settings, raising concerns about fairness and bias, particularly when...
By Chaima Boufaied, Ronnie De Souza Santos, Ann Barcomb
arXiv:2510. 12857v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are now widely deployed in user-facing applications, reaching hundreds of millions of users worldwide.
By Robin Staab, Jasper Dekoninck, Maximilian Baader, Martin Vechev
arXiv:2607. 28934v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly involved in the distribution of scarce resources, raising concerns about biased allocations based on characteristics like race and gender.
By Martin Lukk (University of Toronto)
The paper introduces Collective Bias Mitigation (CBM), a framework that reduces bias in large language models by learning fine‑grained model behavior and enabling knowledge sharing among diverse LLMs. CBM systematically explores how to select and organize distinct models to produce fairer responses, outperforming standalone baselines. Experiments demonstrate significant bias reduction, with the Committee topology balancing effectiveness and inference cost.
By Mingzhe Du, Luu Anh Tuan, Xiaobao Wu, Yichong Huang, Yue Liu, Dong Huang, Huijun Liu, Bin Ji, Jie M. Zhang, See-Kiong Ng
arXiv:2610.15961v1 Announce Type: cross
Abstract: Emergent misalignment (EM) occurs when fine-tuning a language model to a narrow task makes it misaligned on unrelated ones. Because organizations now...
By Alex Mart\'i Guiu, Nicolas Zumarraga, Kevin O'Sullivan, Robert Jakob, Anna Hedstr\"om
arXiv:2607. 21300v1 Announce Type: cross Abstract: Machine unlearning has emerged as a tool for removing personal data from trained models to comply with recent AI regulations.
By Lorenzo Orsingher, Thomas De Min, Massimiliano Mancini, Davide Talon, Elisa Ricci
Fair-GPTQ is a quantization method for large language models that incorporates explicit group‑fairness constraints into the quantization objective. By guiding the rounding operation, it reduces bias in generated text, particularly for occupational stereotypes and discriminatory language across gender, race, and religion. The approach maintains at least 90 % of baseline accuracy on zero‑shot benchmarks while preserving the memory and speed benefits of 4‑bit quantization.
By Irina Proskurina, Guillaume Metzler, Julien Velcin