5 citations · 7 across the 4 of their papers we have counts for
6 papers
EvoProbe: Evaluation-Driven Benchmark Evolution for LLM Agents
Qianhong Guo, Wei Xie, Xiaofang Cai +3
Static benchmarks for large language model (LLM) agents face saturation and data contamination risks, motivating continual updates to evaluation tasks. However, aggregate scores an…
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…
AIPsychoBench: Understanding the Psychometric Differences between LLMs and Humans
Wei Xie, Shuoyoucheng Ma, Zhenhua Wang +4
Large Language Models (LLMs) with hundreds of billions of parameters have exhibited human-like intelligence by learning from vast amounts of internet-scale data. However, the unint…
League of LLMs: A Benchmark-Free Paradigm for Mutual Evaluation of Large Language Models
Qianhong Guo, Wei Xie, Xiaofang Cai +7
Although large language models (LLMs) have shown exceptional capabilities across a wide range of tasks, reliable evaluation remains a critical challenge due to data contamination,…
Foot In The Door: Understanding Large Language Model Jailbreaking via Cognitive Psychology
Zhenhua Wang, Wei Xie, Baosheng Wang +4
Large Language Models (LLMs) have gradually become the gateway for people to acquire new knowledge. However, attackers can break the model's security protection ("jail") to access…
Self-Deception: Reverse Penetrating the Semantic Firewall of Large Language Models
Zhenhua Wang, Wei Xie, Kai Chen +3
Large language models (LLMs), such as ChatGPT, have emerged with astonishing capabilities approaching artificial general intelligence. While providing convenience for various socie…