The paper introduces FairTPT, a fairness-aware test‑time prompt tuning method for vision‑language models like CLIP. It jointly minimizes target marginal entropy while maximizing spurious marginal entropy to reduce bias under subpopulation shifts. Experiments show that standard episodic test‑time adaptation can worsen disparities, but FairTPT outperforms existing debiasing methods while preserving overall performance.
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.
arXiv:2606. 14299v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) such as CLIP have become a standard backbone for open-vocabulary recognition, yet their zero-shot predictions remain vulnerable to distribution shifts encountered at deployment.
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.
arXiv:2605. 03403v2 Announce Type: replace-cross Abstract: Group Relative Policy Optimization (GRPO) has recently shown strong performance in post-training large language models and vision-language models.
The paper investigates how post‑training compression techniques—such as pruning, quantization, and distillation—affect demographic fairness in Whisper speech‑recognition models. It finds that pruning and INT4 quantization significantly widen word‑error‑rate gaps between demographic groups, especially for Black/AA and Asian speakers, while distillation tends to reduce these gaps. The study introduces a temporal‑taxation metric to quantify the increased correction effort required for marginalized speakers after compression.
The paper introduces ViD, a vision‑dominant gender bias mitigation framework for large vision‑language models. ViD uses causal analysis of attention patterns and dual mechanisms—backdoor adjustment and refined token selection—to suppress bias while preserving reasoning and generation quality. Experiments show a 14.7% reduction in gender bias on FACET and significant improvements on MS COCO image captioning, all without extra training overhead.
arXiv:2503.05684v2 Announce Type: replace-cross Abstract: Pre-trained foundation models can be efficiently adapted for specific tasks using Low-Rank Adaptation (LoRA), but the fairness properties of...
arXiv:2607. 28319v1 Announce Type: cross Abstract: This work presents Fairness Pruning, a lightweight structural intervention method designed for the management and future mitigation of demographic bias in large language models (LLMs).
arXiv:2605.28036v2 Announce Type: replace Abstract: Diffusion models steer conditional generation with a tunable guidance scale to trade off prompt alignment and diversity. However, existing debiasin...
arXiv:2608.21415v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) have achieved remarkable performance across a wide range of tasks; however, they often inherit social biases fro...
arXiv:2605. 14746v2 Announce Type: replace Abstract: While large language models (LLMs) are trained to align with human values, their generations may still violate safety constraints.
arXiv:2603. 13683v4 Announce Type: replace-cross Abstract: Although debiased large language models (LLMs) excel at handling known or low-bias prompts, they often fail on unfamiliar and high-bias prompts.