On the Self-Verification Limitations of Large Language Models on Reasoning and Planning Tasks · HackerPapers discussions

On the Self-Verification Limitations of Large Language Models on Reasoning and Planning Tasks — mentioned by YeGoblynQueenne

Thu, 13 Aug 2026 19:13:24 GMT

Thanks, but I can't see that in the article by Anthropic. AFAICT the "650 ideas" that were wrong were all generated independently of each other. I don't agree that LLMs can evaluate an experiment. There's nothing in LLM training that makes them capable of telling what is e.g. a correct hypothesis from an incorrect one. I know that is a common claim particularly encouraged by AI companies but whenever that claim has been studied systematically and carefully the result is that self-verification doesn't work. For example, see: On the Self-Verification Limitations of Large Language Models on…

Paper and discussion history. A mention is not an endorsement.

On the Self-Verification Limitations of Large Language Models on Reasoning and Planning Tasks — mentioned by dudeinhawaii

Wed, 30 Apr 2025 02:21:09 GMT

I see a lot of threads pitting models against each other (or whole swarms of them) in the hope that "wisdom of crowds" will magically appear. After a stack of experiments of my own—and after watching the recent ASU/Microsoft-Research work [1].. I've landed on a simpler takeaway: An LLM is a terrible verifier of another LLM. Subbarao Kambhampati's "(How) Do LLMs Reason/Plan?" talk shows GPT-4 confidently producing provably wrong graph-coloring proofs until a symbolic SAT solver is introduced as the referee [1]. Stechly et al. quantify the problem: letting GPT-4 critique its own answers…

Paper and discussion history. A mention is not an endorsement.