check-logit-lens-decode-attended-image-patches-against TEC-0245 · proposedCheck logit-lens decode of attended image patches against th
At each generated object token, average attention over mid-to-late layers, decode the top-k attended image tokens through the output head, and flag hallucination when no decoded token is semantically similar to the emitted word; then either
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.
At each generated object token, average attention over mid-to-late layers, decode the top-k attended image tokens through the output head, and flag hallucination when no decoded token is semantically similar to the emitted word; then either Filed by the drafting stage from Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination (2608.07302) 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: Detection on 500 COCO images with CHAIR labels: F1 0.7932 vs 0.6842 (SVAR), 0.6811 (InterConf), 0.6182 (Uncertainty Score). Mitigation: lowest CHAIR_S/CHAIR_I on four LVLMs (e.g. 26.8/10.0 vs PAI 29.8/13.2 on LLaVA-1.5-7B) and lowest AMBER CHAIR/Hal while keeping Cover at or above the greedy baseline.. 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.