AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Proximity-Constrained Counterfactual Decoding for Hallucination-Robust Medical VQA

Dwarikanath Mahapatra, Abhijit Das, Manish Pandey, Joy Dhar, Sudipta Roy, Zongyuan Ge, Behzad Bozorgtabar, Imran Razzak

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Preference tuning against hallucination · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add dual proximity guards (s, s_obj) (ablation)PCCD · MIMIC-Diff-VQAAUC: 87.50 -> 89.59Improved
add dual proximity guards (s, s_obj) (ablation)PCCD · Gut-VLM descriptionQAAS / R-Sim: -1.55 QAAS / -0.14 R-Sim when removedImproved
add object-masked proximity guard s_obj (ablation)PCCD · MIMIC-Diff-VQAAUC: 88.10 -> 89.59Improved
add LD-VCD branch to OA-only (ablation)PCCD · MIMIC-Diff-VQAAUC: 88.55 -> 89.59Improved
add OA-VCD branch to LD-only (ablation)PCCD · MIMIC-Diff-VQAAUC: 87.95 -> 89.59Improved
LD-only vs OA-only on attribute-heavy description (ablation)PCCD · Gut-VLM descriptionR-Sim: 4.08 vs 4.05Mixed
use adaptive contrast weight instead of fixed (ablation)PCCD · MIMIC-Diff-VQAAUC: 88.35 -> 89.59Improved
add per-token branch selector over always-OA (ablation)PCCD · MIMIC-Diff-VQAAUC: 88.30 -> 89.59Improved
add per-token branch selector over always-LD (ablation)PCCD · MIMIC-Diff-VQAAUC: 88.00 -> 89.59Improved
add attribute lexicon routing (ablation)PCCD · Gut-VLM descriptionQAAS: -1.40 QAAS when removedImproved
apply PCCD vs greedy under poor attribution (IoU<0.2)PCCD · MIMIC-Diff-VQAdelta AUC: approximately 0 vs AGLA -1.9 ppNo clear effect
apply PCCD vs VASparse on Med-POPE adversarialPCCD · Med-POPE (Adversarial)F1: 77.4 -> 79.7 (+2.3 pp)Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy