10 papers
From Scores to Safe Sets: Exact Safety--Constrained Decoding for Medication Recommendation
Animesh Agarwal, Meysam Ghaffari, Nina Fatehi +2
Recent generative medication recommendation systems ultimately produce sets of drugs, but drug--drug interaction (DDI) constraints depend on the set as a whole. A natural post-hoc…
Verification Turns Capability Gaps into Routing Decisions: Small Language Models for Clinical Documentation
Nina Fatehi, Meysam Ghaffari, Animesh Agarwal +2
Clinical note generation from doctor--patient dialogue is high-volume and hallucination-intolerant: a fabricated laboratory value can create patient-safety risk, not a quality regr…
Personalized State-Transition-Aware Memory for Clinical Agents
Maryam Haghifam, Zahra Rajabi, Yizhou Sun +1
Large language model (LLM) agents that reason over clinical records must track changes in a patient's state while preserving the history needed to understand them. Simply accumulat…
LearnActCoder: Role-Aware Error Memory for Adaptive Clinical Coding Agents
Meysam Ghaffari, Bhaskar Sen, Nasim Sabetpour +3
Clinical coding agents repeatedly encounter the same failure modes, including unsupported codes, missed documented conditions, specificity errors, and procedure-coding convention m…
A Multi-Agent Pipeline for Source-Grounded Synthetic Note Generation from Longitudinal Structured EHR
Nina Fatehi, Reihaneh Hassanzadeh, Meysam Ghaffari +2
Structured EHR is abundant but sparse, coded, and difficult to use directly for note-centric clinical modeling. We present MedNotes, a multi-agent synthetic data generation pipelin…
Structured Evidence Routing for Incident Risk Prediction from Multimodal Longitudinal EHRs
Animesh Agarwal, Meysam Ghaffari, Nina Fatehi +1
Incident risk prediction from longitudinal electronic health records (EHRs) is challenging because relevant signals are multimodal, weak in isolation, and distributed across irregu…
Foundation Agents Meet Agentic Deep Research: Evidence-Grounded Clinical Code Forecasting
Junda Wang, Meysam Ghaffari, Akshat Choube +3
Next-encounter ICD forecasting predicts which standardized diagnosis codes will be documented at a future visit from the longitudinal record available beforehand. The task is prosp…
Context Poisoning as Extreme-Value Attention Interference in Long-Context Language Models
Meysam Ghaffari, Nina Fatehi, Bhaskar Sen +2
Large language models can process increasingly long prompts, yet their ability to locate and use decisive evidence may degrade as irrelevant or confusable context is added. We form…
Text Over Image: Auditing Multimodal Robustness in Synthetic Medical Image Detection
Ching-Hao Chiu, Hao-Wei Chung, Gelei Xu +7
With the rapid adoption of generative AI, synthetic medical images pose growing risks, including diagnostic deception and insurance fraud. Although prior work has explored vision-l…
Reasoning Quality Emerges Early: Data Curation for Reasoning Models
Hongyi Henry Jin, Wenhan Yang, Meysam Ghaffari +2
Supervised fine-tuning (SFT) on a small, high-quality set of long reasoning traces is an effective approach for eliciting strong reasoning capabilities in Large Language Models (LL…