arXiv Machine Learning August 27, 2026 By Yoann Launay, Parameswaran Kamalaruban, Tom Kempton, Stuart Burrell, David Sutton

Fairness-Aware Test-Time Prompt Tuning

Read the original on arXiv Machine Learning →

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.

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 Machine Learning.

arXiv AI

Jul 24

Unlearning Under Imbalance: Benchmarking Fairness in Multimodal LLM Unlearning

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

llms nlp fine-tuning multimodal benchmarks safety

arXiv Machine Learning

Jun 15

What Drives Test-Time Adaptation for CLIP? A Controlled Empirical Study from an Update Perspective

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.

By Jiazhen Huang, Xiao Chen, Zhiming Liu, Yaru Sun, Jingyan Jiang, Zhi Wang

llms multimodal benchmarks

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 Machine Learning

Jun 2

GRPO-TTA: Test-Time Visual Tuning for Vision-Language Models via GRPO-Driven Reinforcement Learning

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.

By Yujun Li, Hongyuan Zhang, Yuan Yuan

llms reinforcement-learning multimodal benchmarks safety

arXiv Computer Vision

Aug 25

Fairness-Aware Low-Rank Representation Fine-Tuning

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...

By Parameswaran Kamalaruban, Mark Anderson, Stuart Burrell, Maeve Madigan, Piotr Skalski, David Sutton

fine-tuning safety

arXiv Machine Learning

Jul 31

Fairness Pruning: Locating Demographic Bias in GLU-MLP Layers via Differential Activations

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).

By Pere Martra, Eugenio Mart\'inez C\'amara, Alfonso Ure\~na L\'opez

llms efficiency benchmarks safety

One email a morning, machine-written

Related stories

Unlearning Under Imbalance: Benchmarking Fairness in Multimodal LLM Unlearning

What Drives Test-Time Adaptation for CLIP? A Controlled Empirical Study from an Update Perspective

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

GRPO-TTA: Test-Time Visual Tuning for Vision-Language Models via GRPO-Driven Reinforcement Learning

Fairness-Aware Low-Rank Representation Fine-Tuning

Fairness Pruning: Locating Demographic Bias in GLU-MLP Layers via Differential Activations