5 papers
BalDRO: A Distributionally Robust Optimization based Framework for Large Language Model Unlearning
Pengyang Shao, Naixin Zhai, Lei Chen +4
As Large Language Models (LLMs) increasingly shape online content, removing targeted information from well-trained LLMs (also known as LLM unlearning) has become critical for web g…
SkillAudit: From Fixed-Suite Benchmarking to Skill-Centered Assessment
Dexu Yu, Youhua Li, Zhaoyang Guan +12
Agent skills have become a practical way to extend large language model agents, but the growing skill ecosystem still lacks a reliable way to judge whether a skill is worth deployi…
Maximizing Local Entropy Where It Matters: Prefix-Aware Localized LLM Unlearning
Naixin Zhai, Pengyang Shao, Binbin Zheng +4
Machine unlearning aims to forget sensitive knowledge from Large Language Models (LLMs) while maintaining general utility. However, existing approaches typically treat all tokens i…
Chain of Mindset: Reasoning with Adaptive Cognitive Modes
Tianyi Jiang, Arctanx An, Hengyi Feng +12
Human problem-solving is never the repetition of a single mindset, by which we mean a distinct mode of cognitive processing. When tackling a specific task, we do not rely on a sing…
Vulnerabilities in AI-generated Image Detection: The Challenge of Adversarial Attacks
Yunfeng Diao, Naixin Zhai, Changtao Miao +4
Recent advancements in image synthesis, particularly with the advent of GAN and Diffusion models, have amplified public concerns regarding the dissemination of disinformation. To a…