arXiv Machine Learning August 10, 2026 By Yong Yang, Roger Newman-Norlund, Xiang Guan, Saeed Ahmadi, Regan Willis, Nadra Salman, Kalil Warren, Sophie Arheix-Parras, Srihari Nelakuditi, Leonardo Bonilha, Christopher Rorden, Rutvik H. Desai, Julius Fridriksson

Recovering Lesion Parameters from Aphasic Picture Naming Error Profiles in Large Language Models

Read the original on arXiv Machine Learning →

arXiv:2608. 06429v1 Announce Type: cross Abstract: Interpretability methods for large language models (LLMs) describe internal state but do not directly test whether that state is causally sufficient to produce the observed behavior.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

5d ago

Perturbation-based Regional Interpretability through Subtraction Mapping (PRISM): naming-error dissociations in language models and post-stroke aphasia

arXiv:2608. 12717v1 Announce Type: new Abstract: Mechanistic interpretability of large language models lacks spatially resolved, falsifiable tools for testing whether internal components are specialized for distinct cognitive operations.

By Xiang Guan, Roger D. Newman-Norlund, Yong Yang, Saeed Ahmadi, Regan Willis, Nadra Salman, Kalil Warren, Srihari Nelakuditi, Chris Rorden, Leonardo Bonilha, Julius Fridriksson

llms safety

arXiv AI

Jul 14

Lesioned Multimodal Language Models Reproduce Aphasic Picture-Naming Patterns

arXiv:2607. 11621v1 Announce Type: new Abstract: Aphasia following stroke commonly produces systematic naming errors with characteristic profiles, but whether general-purpose language models not designed for clinical simulation can reproduce these patterns remains untested.

By Yong Yang, Xiang Guan, Sophie Arheix-Parras, Saeed Ahmadi, Roger Newman-Norlund, Leonardo Bonilha, Christopher Rorden, Julius Fridriksson, Rutvik H. Desai, Srihari Nelakuditi

llms multimodal

arXiv Machine Learning

Jul 2

Explainability in mulimodal deep transformation models for stroke outcome prediction

arXiv:2504. 06299v2 Announce Type: replace-cross Abstract: Multimodal prediction models based on imaging and clinical data are increasingly used for clinical decision support, yet their interpretability remains limited.

By Lisa Herzog, Jonas Br\"andli, Maurice Schneeberger, Loran Avci, Nordin Dari, Martin H\"ansel, Hakim Baazaoui, Pascal B\"uhler, Susanne Wegener, Beate Sick

diffusion multimodal benchmarks safety

arXiv AI

Jun 19

The Scaffold Effect: How Prompt Framing Drives Apparent Multimodal Gains in Clinical VLM Evaluation

arXiv:2603. 28387v2 Announce Type: replace Abstract: Trustworthy clinical AI requires that performance gains reflect genuine evidence integration rather than surface-level artifacts.

By Doan Nam Long Vu, Simone Balloccu

llms multimodal safety

arXiv AI

1d ago

Large language models as synthetic clinical experts to inform longitudinal rare-disease modeling

arXiv:2608. 16507v1 Announce Type: new Abstract: Due to the limited amount of information, modeling longitudinal rare-disease data can benefit from integrating clinical knowledge.

By Clemens Sch\"achter, Astrid Pechmann, Janbernd Kirschner, Jan Hasenauer, Harald Binder

llms

arXiv AI

1d ago

From Generalist to Specialist: A Context-Fusion Framework for Endoscopic Polyp Reporting with a Frozen VLM

arXiv:2608. 15580v1 Announce Type: new Abstract: Reliable endoscopic polyp reporting requires integrating quantitative lesion sizing, standardized Paris classification, and clinically meaningful morphological description within a single record.

By Ruijie Yang, Yan Zhu, Peiyao Fu, Siyuan Li, Te Luo, Zhihua Wang, Quanlin Li, Pinghong Zhou, Xian Yang, Shuo Wang

llms multimodal

Related stories

Perturbation-based Regional Interpretability through Subtraction Mapping (PRISM): naming-error dissociations in language models and post-stroke aphasia

Lesioned Multimodal Language Models Reproduce Aphasic Picture-Naming Patterns

Explainability in mulimodal deep transformation models for stroke outcome prediction

The Scaffold Effect: How Prompt Framing Drives Apparent Multimodal Gains in Clinical VLM Evaluation

Large language models as synthetic clinical experts to inform longitudinal rare-disease modeling

From Generalist to Specialist: A Context-Fusion Framework for Endoscopic Polyp Reporting with a Frozen VLM