google-research-datasets / GSM-IC

Grade-School Math with Irrelevant Context (GSM-IC) benchmark is an arithmetic reasoning dataset built upon GSM8K, by adding irrelevant sentences in problem descriptions. GSM-IC is constructed to evaluate the distractibility of language models.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

google-research-datasets/GSM-IC Stargazers