arXiv Computation and Language October 9, 2026 By Irina Proskurina, Guillaume Metzler, Julien Velcin

Fair-GPTQ: Bias-Aware Quantization for Large Language Models

Read the original on arXiv Computation and Language →

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

arXiv Computation and Language

Sep 15

Intersectional Fairness in Large Language Models

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

llms nlp benchmarks safety

arXiv Machine Learning

Aug 10

Let's Unlearn Stereotypes Before Decision-Making: Assessing the Impact of Intrinsic Bias Mitigation on Downstream Fairness in LLMs

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

llms rag fine-tuning benchmarks safety

arXiv AI

Oct 28

Fairness Definitions in Language Models Explained

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

llms nlp safety

Hugging Face Trending Papers

Jul 23

QuantiBias: Benchmarking Quantization-Induced Bias in LLMs

Almost every large language model that reaches a broad audience is quantized: trained in full precision, then compressed for efficiency. This step is assumed harmless and its safety is rarely re-checked.

llms efficiency benchmarks safety

arXiv AI

Jul 1

Wait, am I Being Fair? Characterizing Deductive Stereotyping and Mitigating It with Fair-GCG

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

llms benchmarks safety

arXiv Computation and Language

Sep 3

Debias-SparseGPT: Bias-Aware Pruning for Large Language Models

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

llms efficiency safety