arXiv - CSCL: "PlanBench: An Extensible Benchmark for Evaluating…" - Qoto Mastodon

arXiv - CSCL @arxiv_cscl@qoto.org

PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Change. (arXiv:2206.10498v4 [cs.CL] UPDATED)

http://arxiv.org/abs/2206.10498 #arXiv #NLProc

Nov 28, 2023, 03:19 · · arxiv-cscl · · ·

Sign in to participate in the conversation