CoNNS uses an LLM-built concept ontology and cross-patient relabeling to filter noisy negatives, improving zero-shot classification and grounding of chest X-ray findings over prior methods.
In: Proceedings of the AAAI conference on artificial intelligence
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
years
2026 6verdicts
UNVERDICTED 6roles
dataset 1polarities
use dataset 1representative citing papers
A verifiable CBM framework grounds concepts in localized image patches, achieving comparable accuracy to standard CBMs on medical benchmarks while enabling direct inspection of concept correctness.
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.
CARPA generates anatomically faithful synthetic chest X-rays with controlled clinical concept insertions and deletions to expand training coverage and improve model precision, calibration, and reliability on real benchmarks.
A sample-difficulty decorrelation method that attenuates age-dependent confounding in radiology classification by modeling label-conditioned difficulty trends and applying robust Huber-weighted affinity penalties scaled by an Age Coverage Score.
KEPIL integrates medical ontologies and a semantic contrastive loss into vision-language models to achieve state-of-the-art prompt-robust zero-shot disease detection in radiology, with reported AUC gains of 6.37% on CheXpert under prompt variations.
citing papers explorer
-
Concept-Guided Noisy Negative Suppression for Zero-Shot Classification and Grounding of Chest X-Ray Findings
CoNNS uses an LLM-built concept ontology and cross-patient relabeling to filter noisy negatives, improving zero-shot classification and grounding of chest X-ray findings over prior methods.
-
Towards Fine-Grained and Verifiable Concept Bottleneck Models
A verifiable CBM framework grounds concepts in localized image patches, achieving comparable accuracy to standard CBMs on medical benchmarks while enabling direct inspection of concept correctness.
-
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.
-
Clinically Aware Synthetic Image Generation for Concept Coverage in Chest X-ray Models
CARPA generates anatomically faithful synthetic chest X-rays with controlled clinical concept insertions and deletions to expand training coverage and improve model precision, calibration, and reliability on real benchmarks.
-
Robust Mitigation of Age-Dependent Confounding Effects via Sample-Difficulty Decorrelation
A sample-difficulty decorrelation method that attenuates age-dependent confounding in radiology classification by modeling label-conditioned difficulty trends and applying robust Huber-weighted affinity penalties scaled by an Age Coverage Score.
-
KEPIL: Knowledge-Enhanced Prompt-Image Learning for Prompt-Robust Disease Detection
KEPIL integrates medical ontologies and a semantic contrastive loss into vision-language models to achieve state-of-the-art prompt-robust zero-shot disease detection in radiology, with reported AUC gains of 6.37% on CheXpert under prompt variations.