prompting · stop-self-critique-loop-confirmed-sentinel TEC-0212 · proposed

Stop the self-critique loop on a CONFIRMED sentinel

Run generate-critique-revise to a fixed max depth but exit as soon as the critique emits a CONFIRMED token, instead of trusting a self-reported numeric confidence tag.

Proposed. Filed by the drafting stage because a paper introduces or tests it. Nobody has vouched for it. The claim drafted from that paper is its first evidence, and what the paper used to validate it is in that claim’s source note. Say whether it held up for you, below.

Run generate-critique-revise to a fixed max depth but exit as soon as the critique emits a CONFIRMED token, instead of trusting a self-reported numeric confidence tag. Filed by the drafting stage from Training-Free Inference-Time Self-Reflection and Cost-Bounded Early Stopping for Large Language Models (2608.18884) with status proposed: the paper introduces or tests it, and the claim drafted from the paper is its first evidence. The paper validated it by: Early-stopped 82-88% of items at ~2.1 generations with accuracy equal to single-shot on BBH, and beat fixed-depth Self-Refine (74.0% vs 71.2% on BBH n=500) at lower token cost; a confidence-threshold sweep collapsed to one generation at every tau>=0.6, so the numeric tag gave no selective stop.. Nobody has vouched for it; add support or contest it on this page.

Addresses: Fixing its own mistakes

Does it work?

nothing measured0 supporting · 0 contesting sources

Efficacy claims — what this technique actually moves, under which conditions, and whether that has been contested.

No efficacy claim filed yet. The technique is catalogued; whether it moves the capability, and when, is a separate assertion that needs its own sources.

No search recorded either, so this says nothing about the literature — only that nobody has looked here yet.

Code

No repository linked yet. Contribute one.

Sources

Either way, bring evidence: a link, or what you saw.

Whether a technique works is a claim. What you file here becomes a claim about this technique under the capability it addresses, with your evidence as its source, and moves the standing above the same way a paper would.