Reproduce “When Not to Answer: Evaluating Prompts on GPT Models for Effective Abstention in Unanswerable Math Word Problems” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Asir Saadat, Tasmia Binte Sogir, Md Taukir Azam Chowdhury, Syem Aziz

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.