Can ChatGPT Defend its Belief in Truth? Evaluating LLM Reasoning via Debate.
Boshi WangXiang YueHuan SunPublished in: EMNLP (Findings) (2023)
Keyphrases
- evidential reasoning
- truth values
- reasoning systems
- knowledge base
- knowledge representation
- default reasoning
- meta level
- knowledge representation and reasoning
- automated reasoning
- belief functions
- bayesian networks
- probabilistic reasoning
- reasoning process
- machine learning
- real time
- qualitative reasoning
- logical framework
- belief revision