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.
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...
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.
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.
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.
arXiv:2606. 30989v1 Announce Type: cross Abstract: Warning: This paper contains several toxic and offensive statements.
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.
The paper presents a comprehensive evaluation of post‑training quantization (PTQ) techniques for large language models (LLMs), addressing gaps in prior work by conducting fair, large‑scale experiments on text‑only LLMs. It decouples quantization into pre‑quantization transformation and error mitigation, systematically studies granularity, symmetry, and data formats (MXFP4, NVFP4), and finds that rotation‑based transformations and low‑rank compensation with GPTQ can improve performance, while finer granularity and asymmetric quantization benefit activations more than weights. The study highlights the importance of understanding component interactions and the impact of scaling factor formats on low‑bit quantization performance.
Post‑training quantization of large language models reduces memory usage but can alter social biases in ways that aggregate metrics miss. In a large‑scale study of 50 quantized models on PostTrainingBiasBench, the authors discovered a phenomenon called quantization‑induced bias flipping, where up to 21% of responses switch from biased to unbiased or vice versa, especially for uncertain predictions and stronger quantization (4‑bit vs 8‑bit). These flips lead to asymmetric impacts across demographic groups, with some groups experiencing up to an 18.6% worsening of bias while others improve by 14.1%, resulting in misleadingly neutral overall scores.
arXiv:2608. 13624v1 Announce Type: cross Abstract: Large Audio Language Models (LALMs) have seen increasing use for audio understanding tasks such as speech recognition and audio question answering, raising concerns about fairness across demographic subgroups.
arXiv:2601. 23221v2 Announce Type: replace Abstract: As acquiring reliable ground-truth labels is usually costly, or infeasible, crowdsourcing and aggregation of noisy human annotations is the typical resort.
arXiv:2609.16321v1 Announce Type: cross Abstract: Existing fairness analysis tools predominantly operate as post-training evaluation frameworks, requiring practitioners to complete the full model dev...
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.