Large Language Models Cannot Self-Correct Reasoning Yet · HackerPapers discussions

Large Language Models Cannot Self-Correct Reasoning Yet — mentioned by johnbarron

Tue, 25 Aug 2026 08:28:48 GMT

It does not work because the errors compound and also are most times correlated. "Nine Judges, Two Effective Votes: Correlated Errors Undermine LLM Evaluation Panels" - https://arxiv.org/abs/2605.29800 "From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration" - https://arxiv.org/abs/2605.29800 "Large Language Models Cannot Self-Correct Reasoning Yet" - https://arxiv.org/abs/2310.01798 "Correlated Errors in Large Language Models" - https://proceedings.mlr.press/v267/kim25e.html "Partially Correlated Verifier Cascades in LLM Harnesses: Concave Log-Odds…

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

Large Language Models Cannot Self-Correct Reasoning Yet — mentioned by flir

Thu, 30 Jul 2026 09:36:34 GMT

But you can't read the original! That's why you built the pipeline in the first place! Only people who can read both versions can have a grounded opinion on whether or not the translation is accurate. C'mon man, I know criticisms of your baby feel like attacks on you, but take a step back. You must see that "the name of the author of the pipeline is public knowledge" is not a sensible response to "nobody who can read both versions has attested to its accuracy in public". Right now, everybody believes that LLMs can't self-correct (see https://arxiv.org/abs/2310.01798) and that they hallucinate…

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

Large Language Models Cannot Self-Correct Reasoning Yet — mentioned by bofadeez

Sun, 23 Mar 2025 05:55:32 GMT

This is really useful. LLMs need external feedback to self-correct reasoning. https://arxiv.org/pdf/2310.01798

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

Large Language Models Cannot Self-Correct Reasoning Yet — mentioned by bofadeez

Mon, 16 Sep 2024 15:01:23 GMT

Not going to work - https://arxiv.org/abs/2310.01798

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

Large Language Models Cannot Self-Correct Reasoning Yet — mentioned by bofadeez

Sun, 11 Aug 2024 20:39:09 GMT

That works if the LLM has adequate external feedback from a terminal and browser in context with the past trial etc. It can't self-correct its own reasoning: https://arxiv.org/abs/2310.01798

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

Large Language Models Cannot Self-Correct Reasoning Yet — mentioned by astrange

Wed, 24 Apr 2024 05:42:15 GMT

Self-reflection and chain-of-thought are different things; CoT is about writing out the intermediate steps to an answer it can't immediately reach. Self-reflection doesn't work well though: https://arxiv.org/abs/2310.01798

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

Large Language Models Cannot Self-Correct Reasoning Yet — HN submission

Wed, 08 Nov 2023 20:43:17 GMT

LLMs cannot self-correct reasoning yet

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Large Language Models Cannot Self-Correct Reasoning Yet — mentioned by rvz

Mon, 16 Oct 2023 16:30:34 GMT

> The implications are vast. We may be able to translate between languages that have never had a “Rosetta Stone”. Any animals that have a true language could have it decoded. And while an LLM that’s gotten an 8 year old’s understanding of balancing assorted items isn’t that useful, an LLM that’s got a baby whale’s grasp on whale language would be revolutionary. Given that almost no-one trusts these LLMs for anything serious beyond creative / BS generating uses, this article does a lot of glossing over the reliability of their outputs and focuses more on such utopian promises with claims of…

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

Large Language Models Cannot Self-Correct Reasoning Yet — mentioned by montebicyclelo

Mon, 09 Oct 2023 19:22:08 GMT

The paper: https://arxiv.org/pdf/2310.01798.pdf > Our research shows that LLMs are not yet capable of self-correcting their reasoning The paper actually just shows that the particular "self-correction" strategy and set of prompts they used doesn't help for the tasks they looked at, for the models they looked at. It may be the case in general, but it may not. > it is plausible that there exist specific prompts or strategies that could enhance the reasoning performance of models for particular benchmarks Seems they agree. So the wording of the title/conclusion is too strong. > searching such…

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

Large Language Models Cannot Self-Correct Reasoning Yet — mentioned by nyrikki

Mon, 09 Oct 2023 18:28:31 GMT

Pre-print https://arxiv.org/abs/2310.01798

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