penalize-tokens-low-vision-ablation-log-prob-gap TEC-0154 · proposedPenalize tokens with a low vision-ablation log-prob gap
Run a second decoding pass with the visual features zeroed, score each candidate token by the log-probability difference between the two paths, and subtract a decaying penalty from candidates whose score falls below a threshold.
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.
Run a second decoding pass with the visual features zeroed, score each candidate token by the log-probability difference between the two paths, and subtract a decaying penalty from candidates whose score falls below a threshold. Filed by the drafting stage from What Do Hallucinations Reveal About Multimodal Reasoning? Diagnosing Visual Grounding Failures via Contrastive Decoding Probes (2609.16646) 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: Compared against Sample, Beam, OPERA, VCD, AGLA, SID and ICD on five benchmarks with LLaVA-1.5, InstructBLIP, Shikra. Large gain only on MMHalBench (3.55 overall vs 1.69 for OPERA, hallucination ratio 0.44 vs 0.74-0.83, single GPT judge over 96 samples); roughly tied or worse on HallusionBench, CHAIR sentence level, and MMMU. Outputs are shorter (95.3 vs 101.8 tokens), and length-normalized CHAIRs margins are small and reverse on Shikra.. 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.