6 papers
Jailbreak Context Lingers: Divergent Safety Routing and Its Cross-Task Predictability in Tool Agents
Xi Wang, Songlei Jian, Yiming Zhang +5
As large language models increasingly operate as tool-using agents, post-jailbreak safety feedback is often assumed to serve as a reliable safeguard; however, how lingering jailbre…
SkillSight: Calibrating Generic Content Bias for Skill Retrieval
Jinying Xiao, Bin Li, Xiaopeng Li +7
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…
Outlier Smoothing with Closed-Form Rotations for W4A4 Large Language Model Quantization
Jinying Xiao, Bin Ji, Shasha Li +8
Large Language Models (LLMs) quantization facilitates deploying LLMs in resource-limited settings, but existing methods that combine incompatible gradient optimization and quantiza…
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…
Camel: Energy-Aware LLM Inference on Resource-Constrained Devices
Hao Xu, Long Peng, Shezheng Song +5
Most Large Language Models (LLMs) are currently deployed in the cloud, with users relying on internet connectivity for access. However, this paradigm faces challenges such as netwo…
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…