11 papers
SkillSight: Calibrating Generic Content Bias for Skill Retrieval
Jinying Xiao, Bin Li, Bin Ji +9
As large language model agents gain access to increasingly large skill libraries, retrieving the right skill becomes critical to reliable capability selection and execution. Existi…
EMSEdit: Efficient Multi-Step Meta-Learning-based Model Editing
Xiaopeng Li, Shasha Li, Xi Wang +7
Large Language Models (LLMs) power numerous AI applications, yet updating their knowledge remains costly. Model editing provides a lightweight alternative through targeted paramete…
Rethinking Residual Distribution in Locate-then-Edit Model Editing
Xiaopeng Li, Shanwen Wang, Shasha Li +4
Model editing enables targeted updates to the knowledge of large language models (LLMs) with minimal retraining. Among existing approaches, locate-then-edit methods constitute a pr…
JPU: Bridging Jailbreak Defense and Unlearning via On-Policy Path Rectification
Xi Wang, Songlei Jian, Shasha Li +5
Despite extensive safety alignment, Large Language Models (LLMs) often fail against jailbreak attacks. While machine unlearning has emerged as a promising defense by erasing specif…
MOSABench: Multi-Object Sentiment Analysis Benchmark for Evaluating Multimodal Large Language Models Understanding of Complex Image
Shezheng Song, Chengxiang He, Shan Zhao +4
Multimodal large language models (MLLMs) have shown remarkable progress in high-level semantic tasks such as visual question answering, image captioning, and emotion recognition. H…
Stand on The Shoulders of Giants: Building JailExpert from Previous Attack Experience
Xi Wang, Songlei Jian, Shasha Li +9
Large language models (LLMs) generate human-aligned content under certain safety constraints. However, the current known technique ``jailbreak prompt'' can circumvent safety-aligne…