arXiv - CSCL: "LatEval: An Interactive LLMs Evaluation Benchmark…" - Qoto Mastodon

arXiv - CSCL @arxiv_cscl@qoto.org

LatEval: An Interactive LLMs Evaluation Benchmark with Incomplete Information from Lateral Thinking Puzzles. (arXiv:2308.10855v2 [cs.CL] UPDATED)

http://arxiv.org/abs/2308.10855 #arXiv #NLProc

Sep 22, 2023, 03:17 · · arxiv-cscl · · ·

Sign in to participate in the conversation