self-critique-without-grounding-unreliablemechanismsingle 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
- Intrinsic self-correction (review-and-revise with no external feedback) did not improve accuracy on GSM8K or CommonSenseQA and often degraded it.
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
- Prompting a model to generate its own feedback on a draft output and revise accordingly improves quality on open-ended generation tasks (dialogue, code, review-writing) over a single-shot attempt.Fixing its own mistakes · contested
- Reflect-and-retry raises task success when the feedback in the loop is a genuine external signal — a failing test, a compiler error, an environment outcome — but not when the "feedback" is the model's own unaided critique. The grounding, not the reflection step, is what does the work.Fixing its own mistakes · contested
- On verifiable instructions such as length and format constraints, strong models still fail a meaningful share, and failures grow when several constraints apply at once.Following an unfamiliar procedure
- In UI-to-code generation, where a rendered screenshot gives genuine external feedback, iterative self-critique still drifts below the initial draft over ten rounds, because a code edit changes the rendering non-locally and a fix for one region breaks regions that were already faithful; restricting each round to one typed, scoped repair target and carrying past targets forward as an avoid-list reduces that drift.Generating and editing working code · unreviewed
- The agent that produced an artifact is a biased judge of it — it holds the context and the incentives that skew its assessment — so verification belongs with a deterministic sensor or a separate verifier that reports failures back rather than rewriting the output, and in a multi-agent system the verifier is the one component no agent may override.Fixing its own mistakes · unreviewed
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.