Oyvind Tafjord

1 article on SOTA Papers

Computer SciencePick

Neuro-Symbolic Reasoning Improves LLM Accuracy by 12-18%

Generating natural language explanations then verifying them symbolically outperforms chain-of-thought prompting.

cs.AIcs.LGcs.CL
Aug 5, 202410 min2408.01234 Code available