self-critique-without-grounding-unreliable
mechanismsingle paper

Without an external, ground-truth signal — a failing test, a compiler error, a verifier's output — a model's own critique of its reasoning is not a reliable improvement signal, and asking it to review and revise a correct answer often turns it into a wrong one.

Evidence for: No one should be judge in their own cause (holds)

Capability: Fixing its own mistakes · Reasoning, Math

Observed on

2023, GPT-3.5/GPT-4 class reasoning benchmarks.

Sources

Status: activeLast checked: 2026-09-03Evidence activityHow much the field cites the sources under this claimvery heavily cited in the last 12 months503 in 12mo · 1164 total — Large Language Models Cannot Self-Correct Reasoning Yet
Contest this claim

Disagreeing is the most useful thing you can do here. Both sides of every contested claim in this catalog were assembled by the same person, which is its weakest point.

Related claims

Notes

Single-paper strength is honest here — this is widely cited and discussed, but I don't yet have an independent replication specifically isolating the no-feedback condition the way this paper does.