PreprintarXiv.org2024
Improving Legibility of LLM Outputs
J. Kirchner, Yining Chen, Harri Edwards, et al.
Proposes legibility training via a Prover-Verifier Game to make LLM chain-of-thought reasoning easier for humans to verify, improving trust in model outputs.
81Jul 18, 2024Large Language ModelsChain Of Thought
arXiv