Conformal abstention from self-consistency
Draw k responses, have the model count how many match each candidate, use that match score as confidence, and set the abstention threshold on a labelled calibration set with conformal prediction so the expected error among answered question
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.
Draw k responses, have the model count how many match each candidate, use that match score as confidence, and set the abstention threshold on a labelled calibration set with conformal prediction so the expected error among answered question Filed by the drafting stage from Mitigating LLM Hallucinations via Conformal Abstention (2405.01563) 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: Hallucination rate versus abstention rate curves on TriviaQA and Temporal Sequences against log-probability and prior self-consistency baselines; error bound verified empirically against manual labels on a 100-item calibration set.. 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.