All 18 audited MLLMs exhibit order sensitivity with per-facet flip rates of 24-50%, exceeding same-order decoder noise.
arXiv preprint arXiv:2509.03986 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Domain specialization does not consistently improve clinical LLM robustness to meaning-preserving prompt variations, as shown by new sensitivity metrics on DiagnosisQA and MedQA.
citing papers explorer
-
Same Evidence, Different Answer: Auditing Order Sensitivity in Multimodal Large Language Models
All 18 audited MLLMs exhibit order sensitivity with per-facet flip rates of 24-50%, exceeding same-order decoder noise.
-
Same Patient, Different Words, Different Diagnosis? Evaluating Semantic Stability in Clinical LLMs
Domain specialization does not consistently improve clinical LLM robustness to meaning-preserving prompt variations, as shown by new sensitivity metrics on DiagnosisQA and MedQA.