SurgCheck benchmark reveals that vision-language models for surgical VQA often depend on linguistic shortcuts rather than visual reasoning, shown by consistent performance drops on less-biased questions.
arXiv preprint arXiv:2410.20327 (2024)
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
A trajectory-aware process reward using DTW on sentence embeddings, combined with exact-match in GRPO after SFT, raises mean medical VQA accuracy from 0.598 to 0.689 across six benchmarks.
SemEnrich enriches radiology reports with positive/neutral findings via self-supervised semantic clustering, yielding average gains of 5-7% on COMET, BERT score, Sentence BLEU, CheXbert-F1 and RadGraph-F1 after fine-tuning, plus further gains when cluster info is added to GRPO rewards.
citing papers explorer
-
SurgCheck: Do Vision-Language Models Really Look at Images in Surgical VQA?
SurgCheck benchmark reveals that vision-language models for surgical VQA often depend on linguistic shortcuts rather than visual reasoning, shown by consistent performance drops on less-biased questions.
-
Improving Medical VQA through Trajectory-Aware Process Supervision
A trajectory-aware process reward using DTW on sentence embeddings, combined with exact-match in GRPO after SFT, raises mean medical VQA accuracy from 0.598 to 0.689 across six benchmarks.
-
SemEnrich: Self-Supervised Semantic Enrichment of Radiology Reports for Vision-Language Learning
SemEnrich enriches radiology reports with positive/neutral findings via self-supervised semantic clustering, yielding average gains of 5-7% on COMET, BERT score, Sentence BLEU, CheXbert-F1 and RadGraph-F1 after fine-tuning, plus further gains when cluster info is added to GRPO rewards.