2000 character limit reached
BSBench: will your LLM find the largest prime number? (2506.04535v1)
Published 5 Jun 2025 in cs.CL
Abstract: We propose that benchmarking LLMs on questions which have no reasonable answer actually isn't as silly as it sounds. We also present a benchmark that allows such testing and a method to modify the existing datasets, and discover that existing models demonstrate a performance far from the perfect on such questions. Our code and data artifacts are available at https://github.com/L3G5/impossible-bench