conftrace_

debate

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

non-expert models (1) persuasiveness (1) truthful answers (1) factuality (1) hallucinations (1) black box (1) large language model (1) human evaluation (1) language model (1) reasoning (1)

Papers

Debating with More Persuasive LLMs Leads to More Truthful Answers ICML 2024 Improving Factuality and Reasoning in Language Models through Multiagent Debate ICML 2024