8 papers
Robust LLM Unlearning Against Relearning Attacks: The Minor Components in Representations Matter
Zeguan Xiao, Xuanzhe Xu, Yun Chen +4
Large language model (LLM) unlearning aims to remove specific data influences from pre-trained model without costly retraining, addressing privacy, copyright, and safety concerns.…
Toward Automated Robustness Evaluation of Mathematical Reasoning
Yutao Hou, Zeguan Xiao, Fei Yu +6
Large Language Models (LLMs) have demonstrated remarkable capabilities in various reasoning-intensive tasks. However, these models exhibit unexpected brittleness, often failing on…
Representation-Guided Parameter-Efficient LLM Unlearning
Zeguan Xiao, Lang Mo, Yun Chen +4
Large Language Models (LLMs) often memorize sensitive or harmful information, necessitating effective machine unlearning techniques. While existing parameter-efficient unlearning m…
Modeling LLM Unlearning as an Asymmetric Two-Task Learning Problem
Zeguan Xiao, Siqing Li, Yong Wang +4
Machine unlearning for large language models (LLMs) aims to remove targeted knowledge while preserving general capability. In this paper, we recast LLM unlearning as an asymmetric…
Towards Bridging the Reward-Generation Gap in Direct Alignment Algorithms
Zeguan Xiao, Yun Chen, Guanhua Chen +1
Direct Alignment Algorithms (DAAs), such as Direct Preference Optimization (DPO) and Simple Preference Optimization (SimPO), have emerged as efficient alternatives to Reinforcement…
Enhancing Uncertainty Estimation in LLMs with Expectation of Aggregated Internal Belief
Zeguan Xiao, Diyang Dou, Boya Xiong +2
Large Language Models (LLMs) have achieved remarkable success across a wide range of natural language tasks, but often exhibit overconfidence and generate plausible yet incorrect a…