NAST: Improving Negation Handling in Medical Vision–Language Models through Negation-Aware Selective Training

Ali Abbasi, Mehdi Taghipour, Rahmatollah Beheshti
Proceedings of the 11th Machine Learning for Healthcare Conference, PMLR 340:1-29, 2026.

Abstract

Negation is a fundamental linguistic operation in clinical reporting, yet vision–language models (VLMs) frequently fail to distinguish affirmative from negated medical statements. To systematically characterize this limitation, we introduce MedNega-Bench, a radiology-specific diagnostic benchmark that evaluates polarity sensitivity under controlled clinical conditions, revealing that common medical VLMs consistently confuse negated and non-negated findings. To enable learning beyond simple condition absence, we further construct MedNega-FT, a contextual clinical negation dataset that encodes structured claims and supports attributelevel negations involving location and severity. Building on these resources, we propose Negation-Aware Selective Training (NAST), an interpretability-guided adaptation method that uses causal tracing effects (CTEs) to modulate layer-wise gradient updates during fine-tuning. NAST scales each layer’s update according to its causal contribution to negation processing, transforming mechanistic interpretability signals into a principled optimization rule. Experiments demonstrate improved discrimination of affirmative and negated clinical statements without degrading general vision–language alignment, highlighting the value of causal interpretability for targeted model adaptation in safety-critical medical settings. Code and resources are available at https://github.com/healthylaife/NAST.

Cite this Paper

BibTeX
@InProceedings{pmlr-v340-abbasi26a, title = {NAST: Improving Negation Handling in Medical Vision–Language Models through Negation-Aware Selective Training}, author = {Abbasi, Ali and Taghipour, Mehdi and Beheshti, Rahmatollah}, booktitle = {Proceedings of the 11th Machine Learning for Healthcare Conference}, pages = {1--29}, year = {2026}, editor = {Krishnan, Rahul G. and van Amsterdam, Wouter A. C. and Chopra, Sumit and Overgaard, Shauna and Hughes, Michael and Ötleş, Erkin and Shen, Yiqiu and Shanmugam, Divya and Nayan, Madhur and Engelhard, Matthew and Fackler, Jim and Oberst, Michael}, volume = {340}, series = {Proceedings of Machine Learning Research}, month = {12--14 Aug}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v340/main/assets/abbasi26a/abbasi26a.pdf}, url = {https://proceedings.mlr.press/v340/abbasi26a.html}, abstract = {Negation is a fundamental linguistic operation in clinical reporting, yet vision–language models (VLMs) frequently fail to distinguish affirmative from negated medical statements. To systematically characterize this limitation, we introduce MedNega-Bench, a radiology-specific diagnostic benchmark that evaluates polarity sensitivity under controlled clinical conditions, revealing that common medical VLMs consistently confuse negated and non-negated findings. To enable learning beyond simple condition absence, we further construct MedNega-FT, a contextual clinical negation dataset that encodes structured claims and supports attributelevel negations involving location and severity. Building on these resources, we propose Negation-Aware Selective Training (NAST), an interpretability-guided adaptation method that uses causal tracing effects (CTEs) to modulate layer-wise gradient updates during fine-tuning. NAST scales each layer’s update according to its causal contribution to negation processing, transforming mechanistic interpretability signals into a principled optimization rule. Experiments demonstrate improved discrimination of affirmative and negated clinical statements without degrading general vision–language alignment, highlighting the value of causal interpretability for targeted model adaptation in safety-critical medical settings. Code and resources are available at https://github.com/healthylaife/NAST.} }
Endnote
%0 Conference Paper %T NAST: Improving Negation Handling in Medical Vision–Language Models through Negation-Aware Selective Training %A Ali Abbasi %A Mehdi Taghipour %A Rahmatollah Beheshti %B Proceedings of the 11th Machine Learning for Healthcare Conference %C Proceedings of Machine Learning Research %D 2026 %E Rahul G. Krishnan %E Wouter A. C. van Amsterdam %E Sumit Chopra %E Shauna Overgaard %E Michael Hughes %E Erkin Ötleş %E Yiqiu Shen %E Divya Shanmugam %E Madhur Nayan %E Matthew Engelhard %E Jim Fackler %E Michael Oberst %F pmlr-v340-abbasi26a %I PMLR %P 1--29 %U https://proceedings.mlr.press/v340/abbasi26a.html %V 340 %X Negation is a fundamental linguistic operation in clinical reporting, yet vision–language models (VLMs) frequently fail to distinguish affirmative from negated medical statements. To systematically characterize this limitation, we introduce MedNega-Bench, a radiology-specific diagnostic benchmark that evaluates polarity sensitivity under controlled clinical conditions, revealing that common medical VLMs consistently confuse negated and non-negated findings. To enable learning beyond simple condition absence, we further construct MedNega-FT, a contextual clinical negation dataset that encodes structured claims and supports attributelevel negations involving location and severity. Building on these resources, we propose Negation-Aware Selective Training (NAST), an interpretability-guided adaptation method that uses causal tracing effects (CTEs) to modulate layer-wise gradient updates during fine-tuning. NAST scales each layer’s update according to its causal contribution to negation processing, transforming mechanistic interpretability signals into a principled optimization rule. Experiments demonstrate improved discrimination of affirmative and negated clinical statements without degrading general vision–language alignment, highlighting the value of causal interpretability for targeted model adaptation in safety-critical medical settings. Code and resources are available at https://github.com/healthylaife/NAST.
APA
Abbasi, A., Taghipour, M. & Beheshti, R.. (2026). NAST: Improving Negation Handling in Medical Vision–Language Models through Negation-Aware Selective Training. Proceedings of the 11th Machine Learning for Healthcare Conference, in Proceedings of Machine Learning Research 340:1-29 Available from https://proceedings.mlr.press/v340/abbasi26a.html.

Related Material