4 papers
Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training
Youliang Yuan, Wenxiang Jiao, Wenxuan Wang +5
This study addresses a critical gap in safety tuning practices for Large Language Models (LLMs) by identifying and tackling a refusal position bias within safety tuning data, which…
How Far Are We on the Decision-Making of LLMs? Evaluating LLMs' Gaming Ability in Multi-Agent Environments
Jen-tse Huang, Eric John Li, Man Ho Lam +7
Decision-making is a complex process requiring diverse abilities, making it an excellent framework for evaluating Large Language Models (LLMs). Researchers have examined LLMs' deci…
Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM's Reasoning Capability
Zicheng Lin, Tian Liang, Jiahao Xu +7
Mathematical reasoning tasks pose significant challenges for large language models (LLMs) because they require precise logical deduction and sequence analysis. In this work, we int…
Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate
Tian Liang, Zhiwei He, Wenxiang Jiao +6
Modern large language models (LLMs) like ChatGPT have shown remarkable performance on general language tasks but still struggle on complex reasoning tasks, which drives the researc…