MuSR: Testing the Limits of Chain-of-thought with Multistep Soft Reasoning

arXiv:2310.16049v2 Announce Type: replace
Abstract: While large language models (LLMs) equipped with techniques like chain-of-thought prompting have demonstrated impressive capabilities, they still fall short in their ability to reason robustly in complex settings. However, evaluating LLM reasoning is challenging because system capabilities continue to grow while benchmark datasets for tasks like logical deduction have remained static. We introduce MuSR, a dataset for evaluating language models on multistep soft reasoning tasks specified in a natural language narrative. This dataset has two …

abstract arxiv benchmark capabilities cs.cl datasets however language language models large language large language models llm llm reasoning llms prompting reason reasoning tasks testing thought type