Is ChatGPT a Good Causal Reasoner? A Comprehensive Evaluation
Submission Type: Regular Long Paper
Submission Track: Theme Track: Large Language Models and the Future of NLP
Submission Track 2: Resources and Evaluation
Keywords: Causal Reasoning, Large Language Models, Performance Evaluation
TL;DR: Assessing ChatGPT's causal reasoning ability, we find that ChatGPT is good at causal explanation, but has hallucinations in causal reasoning tasks.
Abstract: Causal reasoning ability is crucial for numerous NLP applications. Despite the impressive emerging ability of ChatGPT in various NLP tasks, it is unclear how well ChatGPT performs in causal reasoning.
In this paper, we conduct the first comprehensive evaluation of the ChatGPT's causal reasoning capabilities.
Experiments show that ChatGPT is not a good causal reasoner, but a good causal interpreter. Besides, ChatGPT has a serious hallucination on causal reasoning, possibly due to the reporting biases between causal and non-causal relationships in natural language, as well as ChatGPT's upgrading processes, such as RLHF. The In-Context Learning (ICL) and Chain-of-Thought (COT) techniques can further exacerbate such causal hallucination. Additionally, the causal reasoning ability of ChatGPT is sensitive to the words used to express the causal concept in prompts, and close-ended prompts perform better than open-ended prompts. For events in sentences, ChatGPT excels at capturing explicit causality rather than implicit causality, and performs better in sentences with lower event density and smaller lexical distance between events.
Submission Number: 505
Loading