detect-hallucination-adjacent-layer-attention-drift-plus-masked TEC-0252 · proposedDetect hallucination from adjacent-layer attention drift plu
Compute KL divergence between consecutive layers' cross-modal attention over visual tokens, mask the top-attended region of the layer just before the largest drift, re-query the same token's probability, and feed the drift profile plus the
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.
Compute KL divergence between consecutive layers' cross-modal attention over visual tokens, mask the top-attended region of the layer just before the largest drift, re-query the same token's probability, and feed the drift profile plus the Filed by the drafting stage from Detecting Object Hallucinations in Large Vision-Language Models via Cross-Modal Attention Drifts and Mask-Based Verification (2609.02028) 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: ACC and AUROC against six detection baselines (IC, GLSim, NLL, Entropy, SVAR, DHCP) on three models and three datasets: best in 16 of 18 cells, with COCO-Caption AUROC gains of 5.6/8.4/4.6 points over the best baseline; ablations isolate each component (LLaVA drift-only AUROC 85.7, masking-only 72.8, combined 87.4) and compare masking-layer and masking-region choices.. 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.