4 papers · 1 filter
A Good Plan is Hard to Find: Aligning Models with Preferences is Misaligned with What Helps Users
Nishant Balepur, Matthew Shu, Yoo Yeon Sung +5
To assist users in complex tasks, LLMs generate plans: step-by-step instructions towards a goal. While alignment methods aim to ensure LLM plans are helpful, they train (RLHF) or e…
GuidedBench: Measuring and Mitigating the Evaluation Discrepancies of In-the-wild LLM Jailbreak Methods
Ruixuan Huang, Xunguang Wang, Zongjie Li +2
Despite the growing interest in jailbreak methods as an effective red-teaming tool for building safe and responsible large language models (LLMs), flawed evaluation system designs…
STShield: Single-Token Sentinel for Real-Time Jailbreak Detection in Large Language Models
Xunguang Wang, Wenxuan Wang, Zhenlan Ji +4
Large Language Models (LLMs) have become increasingly vulnerable to jailbreak attacks that circumvent their safety mechanisms. While existing defense methods either suffer from ada…
Split and Merge: Aligning Position Biases in LLM-based Evaluators
Zongjie Li, Chaozheng Wang, Pingchuan Ma +4
Large language models (LLMs) have shown promise as automated evaluators for assessing the quality of answers generated by AI systems. However, these LLM-based evaluators exhibit po…