Large Language Models Are Unconscious of Unreasonability in Math Problems

arXiv:2403.19346v1 Announce Type: new
Abstract: Large language models (LLMs) demonstrate substantial capabilities in solving math problems. However, they tend to produce hallucinations when given questions containing unreasonable errors. In this paper, we study the behavior of LLMs when faced with unreasonable math problems and further explore their potential to address these problems. First, we construct the Unreasonable Math Problem (UMP) benchmark to examine the error detection ability of LLMs. Experiments show that LLMs are able to detect unreasonable errors, but …

abstract arxiv behavior capabilities cs.cl errors explore hallucinations however language language models large language large language models llms math paper questions study type