retrieve-in-context-critiques-weak-model-failure-mode TEC-0178 · proposedRetrieve in-context critiques by weak-model failure mode
Build an offline bank of wrong answers from small same-family models labelled with clustered failure modes plus natural-language critiques, then retrieve critique exemplars for a large model either by its dominant family-level failure profi
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.
Build an offline bank of wrong answers from small same-family models labelled with clustered failure modes plus natural-language critiques, then retrieve critique exemplars for a large model either by its dominant family-level failure profi Filed by the drafting stage from CritICL: Inference-Time Weak-to-Strong Generalization from Small Language Model Failure Modes (2608.27455) 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: Pass@1 on GSM8K, MATH, AMC23, AIME24/25 against zero/1/3/5-shot ICL, self-consistency@3/5/7, self-reflection and LLM-as-judge; CritICL-static reached 49.8 overall on Qwen2.5-32B vs 46.0 for 5-shot fixed and 49.5 for Consistency@7, at 1 generation and 3768 total tokens vs 5440; ablation swapping selection for random/fixed/semantic lost 4-6 points on AMC23/AIME25.. Nobody has vouched for it; add support or contest it on this page.
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
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.