attenuate-hidden-state-modes-hallucination-to-signal-ratio TEC-0241 · proposedAttenuate hidden-state modes by hallucination-to-signal rati
Estimate truthful and hallucination-distortion covariances from paired captions offline, build a closed-form Wiener gain per eigenmode of the distortion covariance, and multiply it into the FFN output projection of deep layers so inference
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.
Estimate truthful and hallucination-distortion covariances from paired captions offline, build a closed-form Wiener gain per eigenmode of the distortion covariance, and multiply it into the FFN output projection of deep layers so inference Filed by the drafting stage from Wiener Representation Filtering for VLM Hallucination Suppression (2608.08167) 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: CHAIR_S/CHAIR_I on 500 MSCOCO images over three seeds against greedy, beam search, DoLa, VCD, OPERA, MARINE, HALC and Nullu (e.g. MiniGPT-4 CHAIR_S 21.20 greedy, 17.67 HALC, 16.87 ours), plus POPE accuracy/F1 and MME Dolan-More profiles; ablations on MiniGPT-4 compare mean-distortion subtraction (CHAIR_S 22.0) and uniform shrinkage (24.0) against the full filter (13.0) at matched layers.. 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.