4 papers
LLM-VA: Resolving the Jailbreak-Overrefusal Trade-off via Vector Alignment
Haonan Zhang, Dongxia Wang, Yi Liu +2
Safety-aligned LLMs suffer from two failure modes: jailbreak (answering harmful inputs) and over-refusal (declining benign queries). Existing vector steering methods adjust the mag…
ORFuzz: Fuzzing the "Other Side" of LLM Safety -- Testing Over-Refusal
Haonan Zhang, Dongxia Wang, Yi Liu +5
Large Language Models (LLMs) increasingly exhibit over-refusal - erroneously rejecting benign queries due to overly conservative safety measures - a critical functional flaw that u…
Sticking to the Mean: Detecting Sticky Tokens in Text Embedding Models
Kexin Chen, Dongxia Wang, Yi Liu +2
Despite the widespread use of Transformer-based text embedding models in NLP tasks, surprising 'sticky tokens' can undermine the reliability of embeddings. These tokens, when repea…
Characterizing and Evaluating the Reliability of LLMs against Jailbreak Attacks
Kexin Chen, Yi Liu, Dongxia Wang +2
Large Language Models (LLMs) have increasingly become pivotal in content generation with notable societal impact. These models hold the potential to generate content that could be…