mask-language-only-self-attention-keep-vision-to TEC-0146 · proposedMask language-only self-attention, keep vision-to-language f
At inference, apply mode-specific attention masks that suppress language-only self-attention in the late decoder layers so text tokens are forced to draw on visual tokens when attributing person attributes.
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 inference, apply mode-specific attention masks that suppress language-only self-attention in the late decoder layers so text tokens are forced to draw on visual tokens when attributing person attributes. Filed by the drafting stage from ViD: Vision-Dominant Gender Bias Mitigation for Large Vision-Language Models (2609.16647) 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: Gender bias score on FACET (0.9274 to 0.9928 for LLaVA), MS COCO (0.6708 to 0.9978), FairFace (0.5988 to 0.8782 for Shikra), against six prior debiasing baselines; POPE accuracy and MMMU score held near baseline (LLaVA 82.63 to 83.06 POPE, 32.4 to 31.8 MMMU); coverage per attention mode reported (V2L 95.8% vs visual-only 9.3%, language-only 4.9%, L2V 0.2%).. 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.