Inspired by the dual-process theory of human cognition from Thinking, Fast and Slow, we introduce PRIME (Planning and Retrieval-Integrated Memory for Enhanced Reasoning), a multi-agent reasoning framework that dynamically integrates System 1 (fast, intuitive thinking) and System 2 (slow, deliberate thinking). PRIME first employs a Quick Thinking Agent to generate a rapid answer; if uncertainty is detected, it then triggers a structured System 2 reasoning pipeline composed of specialized agents for planning, hypothesis generation, retrieval, information integration, and decision-making. This multi-agent design mimics human cognitive processes faithfully and enhances both efficiency and accuracy. Experimental results with LLaMA 3 models demonstrate that PRIME enables open-source LLMs to perform competitively with state-of-the-art closed-source models like GPT-4 and GPT-4o on benchmarks requiring multi-hop and knowledge-grounded reasoning. This research establishes PRIME as a scalable solution for improving LLMs in domains requiring complex, knowledge-intensive reasoning.

Real-world adoption of closed-loop insulin delivery systems (CLIDS) in type 1 diabetes remains low, driven not by technical failure, but by diverse behavioral, psychosocial, and social barriers. We introduce ChatCLIDS, the first benchmark to rigorously evaluate LLM–driven persuasive dialogue for health behavior change. Our framework features a library of expert-validated virtual patients, each with clinically grounded, heterogeneous profiles and realistic adoption barriers, and simulates multi-turn interactions with nurse agents equipped with a diverse set of evidence-based persuasive strategies. ChatCLIDS uniquely supports longitudinal counseling and adversarial social influence scenarios, enabling robust, multi-dimensional evaluation. Our findings reveal that while larger and more reflective LLMs adapt strategies over time, all models struggle to overcome resistance, especially under realistic social pressure. These results highlight critical limitations of current LLMs for behavior change, and offer a high-fidelity, scalable testbed for advancing trustworthy persuasive AI in healthcare and beyond.

This survey reviews LLM-based multi-agent systems for clinical and healthcare workflows, including diagnosis, triage, consultation, discharge, mental health, and EHR-linked decision support.We define AI hospitals as workflow-level clinical systems in which agents take explicit roles, hand off shared state, use EHR-or guideline-grounded tools, and operate with safety gates and audit-ready logs.We argue that these systems should be compared at the workflow level, rather than only by model components or end-task accuracy, because clinical action, evidence, and accountability are expressed through state transitions and handoffs.We organize the literature through a workflowlevel taxonomy covering roles and handoffs, memory and evidence, tools, and reasoning, control, and escalation.We further synthesize major workflow settings and task families, introduce a four-layer evaluation stack spanning safety, process, outcome, and operations, and connect model capabilities to workflow observables relevant to deployment.Finally, we present Integration Readiness Levels (IRL1-IRL6), task-level instrumentation requirements, and recurring workflow failure modes as a practical framework for comparing, evaluating, and deploying clinical LLM agents and AI hospitals.1

, which leverages information retrieval specifically for generated sub-questions and re-answers these sub-questions with the relevant contextual information. Additionally, a Retrieval-Augmented Factuality Scorer is proposed to replace the original discriminator, prioritizing reasoning paths that meet high standards of factuality. Experimental results with LLaMA 3.1 show that RARE enables open-source LLMs to achieve competitive performance with top closed-source models like GPT-4 and GPT-4o. This research establishes RARE as a scalable solution for improving LLMs in domains where logical coherence and factual integrity are critical.

Large language models (LLMs) have demonstrated promising performance on medical benchmarks; however, their ability to perform medical calculations, a crucial aspect of clinical decision-making, remains underexplored and poorly evaluated. Existing benchmarks often assess only the final answer with a wide numerical tolerance, overlooking systematic reasoning failures and potentially causing serious clinical misjudgments. In this work, we revisit medical calculation evaluation with a stronger focus on clinical trustworthiness. First, we clean and restructure the MedCalc-Bench dataset and propose a new step-by-step evaluation pipeline that independently assesses formula selection, entity extraction, and arithmetic computation. Under this granular framework, the accuracy of GPT-4o drops from 62.7% to 43.6%, revealing errors masked by prior evaluations. Second, we introduce an automatic error analysis framework that generates structured attribution for each failure mode. Human evaluation confirms its alignment with expert judgment, enabling scalable and explainable diagnostics. Finally, we propose a modular agentic pipeline, MedRaC, that combines retrieval-augmented generation and Python-based code execution. Without any fine-tuning, MedRaC improves the accuracy of different LLMs from 16.35% up to 53.19%. Our work highlights the limitations of current benchmark practices and proposes a more clinically faithful methodology. By enabling transparent and transferable reasoning evaluation, we move closer to making LLM-based systems trustworthy for real-world medical applications.

Discharge communication is a critical yet underexplored component of patient care, where the goal shifts from diagnosis to education.While recent large language model (LLM) benchmarks emphasize in-visit diagnostic reasoning, they fail to evaluate models' ability to support patients after the visit.We introduce DischargeSim, a novel benchmark that evaluates LLMs on their ability to act as personalized discharge educators.DischargeSim simulates post-visit, multi-turn conversations between LLM-driven DoctorAgents and Pa-tientAgents with diverse psychosocial profiles (e.g., health literacy, education, emotion).Interactions are structured across six clinically grounded discharge topics and assessed along three axes: (1) dialogue quality via automatic and LLM-as-judge evaluation, (2) personalized document generation including free-text summaries and structured AHRQ checklists, and ( 3) patient comprehension through a downstream multiple-choice exam.Experiments across 18 LLMs reveal significant gaps in discharge education capability, with performance varying widely across patient profiles.Notably, model size does not always yield better education outcomes, highlighting trade-offs in strategy use and content prioritization.DischargeSim offers a first step toward benchmarking LLMs in post-visit clinical education and promoting equitable, personalized patient support. 1 .* indicates equal contribution 1 The source code is released at: https://github.com/ michaels6060/DischargeSim with CC-BY-NC 4.0 license.Discharge notes …… -Discharge Diagnoses -Discharge Medications -Discharge Condition -Discharge Instructions -Follow-up Plan : You'll be taking furosemide 40 mg by mouth every morning-it helps reduce fluid overload and also lowers your blood pressure.But because it can make you urinate more and lower potassium, you're also on potassium chloride 10 mEq daily.I took the 40 mg furosemide today and felt lightheaded.Should I be worried?: It's not uncommon.Make sure to take the 40 mg dose after breakfast, not on an empty stomach.Also, rise slowly from sitting or lying down.If the dizziness continues or worsens, call us-we may lower the dose or adjust your schedule.…

Automatic question generation (QG) is essential for AI and NLP, particularly in intelligent tutoring, dialogue systems, and fact verification. Generating multiple-choice questions (MCQG) for professional exams, like the United States Medical Licensing Examination (USMLE), is particularly challenging, requiring domain expertise and complex multi-hop reasoning for high-quality questions. However, current large language models (LLMs) like GPT-4 struggle with professional MCQG due to outdated knowledge, hallucination issues, and prompt sensitivity, resulting in unsatisfactory quality and difficulty. To address these challenges, we propose MCQG-SRefine, an LLM self-refine-based (Critique and Correction) framework for converting medical cases into high-quality USMLE-style questions. By integrating expert-driven prompt engineering with iterative self-critique and self-correction feedback, MCQG-SRefine significantly enhances human expert satisfaction regarding both the quality and difficulty of the questions. Furthermore, we introduce an LLM-as-Judge-based automatic metric to replace the complex and costly expert evaluation process, ensuring reliable and expert-aligned assessments.

Prior research on Twitter (now X) data has provided positive evidence of its utility in developing supplementary health surveillance systems. In this study, we present a new framework to surveil public health, focusing on mental health (MH) outcomes. We hypothesize that locally posted tweets are indicative of local MH outcomes and collect tweets posted from 765 neighborhoods (census block groups) in the USA. We pair these tweets from each neighborhood with the corresponding MH outcome reported by the Center for Disease Control (CDC) to create a benchmark dataset, LocalTweets. With LocalTweets, we present the first population-level evaluation task for Twitter-based MH surveillance systems. We then develop an efficient and effective method, LocalHealth, for predicting MH outcomes based on LocalTweets. When used with GPT3.5, LocalHealth achieves the highest F1-score and accuracy of 0.7429 and 79.78%, respectively, a 59% improvement in F1-score over the GPT3.5 in zero-shot setting. We also utilize LocalHealth to extrapolate CDC’s estimates to proxy unreported neighborhoods, achieving an F1-score of 0.7291. Our work suggests that Twitter data can be effectively leveraged to simulate neighborhood-level MH outcomes.

Large Language Models (LLMs) such as GPT & Llama have demonstrated significant achievements in summarization tasks but struggle with factual inaccuracies, a critical issue in clinical NLP applications where errors could lead to serious consequences.To counter the high costs and limited availability of expert-annotated data for factual alignment, this study introduces an innovative pipeline that utilizes >100B parameter GPT variants like GPT-3.5 & GPT-4 to act as synthetic experts to generate high-quality synthetics feedback aimed at enhancing factual consistency in clinical note summarization.Our research primarily focuses on edit feedback generated by these synthetic feedback experts without additional human annotations, mirroring and optimizing the practical scenario in which medical professionals refine AI system outputs.Although such 100B+ parameter GPT variants have proven to demonstrate expertise in various clinical NLP tasks, such as the Medical Licensing Examination, there is scant research on their capacity to act as synthetic feedback experts and deliver expert-level edit feedback for improving the generation quality of weaker (<10B parameter) LLMs like GPT-2 (1.5B) & Llama 2 (7B) in clinical domain.So in this work, we leverage 100B+ GPT variants to act as synthetic feedback experts offering expert-level edit feedback, that is used to reduce hallucinations and align weaker (<10B parameter) LLMs with medical facts using two distinct alignment algorithms (DPO & SALT), endeavoring to narrow the divide between AIgenerated content and factual accuracy.This highlights the substantial potential of LLMbased synthetic edits in enhancing the alignment of clinical factuality 1 . * indicates equal contribution † Presently in AMD AI

Videos capture the evolution of continuous dynamical systems over time in the form of discrete image sequences. Recently, video generation models have been widely used in robotic research. However, generating controllable videos from image-text pairs is an important yet underexplored research topic in both robotic and computer vision communities. This paper introduces an innovative and elegant framework named TiV-ODE, formulating this task as modeling the dynamical system in a continuous space. Specifically, our framework leverages the ability of Neural Ordinary Differential Equations (Neural ODEs) to model the complex dynamical system depicted by videos as a nonlinear ordinary differential equation. The resulting framework offers control over the generated videos’ dynamics, content, and frame rate, a feature not provided by previous methods. Experiments demonstrate the ability of the proposed method to generate highly controllable and visually consistent videos and its capability of modeling dynamical systems. Overall, this work is a significant step towards developing advanced controllable video generation models that can handle complex and dynamic scenes.

OBJECTIVES: To enhance the performance of large language models (LLMs) in biomedical natural language processing (BioNLP) by introducing a domain-specific instruction dataset and examining its impact when combined with multi-task learning principles. MATERIALS AND METHODS: We created the BioInstruct, comprising 25 005 instructions to instruction-tune LLMs (LLaMA 1 and 2, 7B and 13B version). The instructions were created by prompting the GPT-4 language model with 3-seed samples randomly drawn from an 80 human curated instructions. We employed Low-Rank Adaptation (LoRA) for parameter-efficient fine-tuning. We then evaluated these instruction-tuned LLMs on several BioNLP tasks, which can be grouped into 3 major categories: question answering (QA), information extraction (IE), and text generation (GEN). We also examined whether categories (eg, QA, IE, and generation) of instructions impact model performance. RESULTS AND DISCUSSION: Comparing with LLMs without instruction-tuned, our instruction-tuned LLMs demonstrated marked performance gains: 17.3% in QA on average accuracy metric, 5.7% in IE on average F1 metric, and 96% in Generation tasks on average GPT-4 score metric. Our 7B-parameter instruction-tuned LLaMA 1 model was competitive or even surpassed other LLMs in the biomedical domain that were also fine-tuned from LLaMA 1 with vast domain-specific data or a variety of tasks. Our results also show that the performance gain is significantly higher when instruction fine-tuning is conducted with closely related tasks. Our findings align with the observations of multi-task learning, suggesting the synergies between 2 tasks. CONCLUSION: The BioInstruct dataset serves as a valuable resource and instruction tuned LLMs lead to the best performing BioNLP applications.

Automatic International Classification of Diseases (ICD) coding aims to assign multiple ICD codes to a medical note with an average of 3,000+ tokens. This task is challenging due to the high-dimensional space of multi-label assignment (155,000+ ICD code candidates) and the long-tail challenge - Many ICD codes are infrequently assigned yet infrequent ICD codes are important clinically. This study addresses the long-tail challenge by transforming this multi-label classification task into an autoregressive generation task. Specifically, we first introduce a novel pretraining objective to generate free text diagnosis and procedure descriptions using the SOAP structure, the medical logic physicians use for note documentation. Second, instead of directly predicting the high dimensional space of ICD codes, our model generates the lower dimension of text descriptions, which then infer ICD codes. Third, we designed a novel prompt template for multi-label classification. We evaluate our Generation with Prompt (GP) model with the benchmark of all code assignment (MIMIC-III-full) and few shot ICD code assignment evaluation benchmark (MIMIC-III-few). Experiments on MIMIC-III-few show that our model performs with a marco F1 30.2, which substantially outperforms the previous MIMIC-III-full SOTA model (marco F1 4.3) and the model specifically designed for few/zero shot setting (marco F1 18.7). Finally, we design a novel ensemble learner, a cross attention reranker with prompts, to integrate previous SOTA and our best few-shot coding predictions. Experiments on MIMIC-III-full show that our ensemble learner substantially improves both macro and micro F1, from 10.4 to 14.6 and from 58.2 to 59.1, respectively.

Recent work has shown the promise of learning with human feedback paradigms to produce human-determined high-quality text.Existing works use human feedback to train large language models (LLMs) in general domain abstractive summarization and have obtained summary quality exceeding traditional likelihood training.In this paper, we focus on a less explored form of human feedback -Human Edits.We propose Sequence Alignment (un)Likelihood Training (SALT), a novel technique to use both the human-edited and modelgenerated data together in the training loop.In addition, we demonstrate simulating Human Edits with ground truth summaries coming from existing training data -Imitation edits, along with the model-generated summaries obtained after the training, to reduce the need for expensive human-edit data.In our experiments, we extend human feedback exploration from general domain summarization to medical domain summarization.Our results 1 demonstrate the effectiveness of SALT in improving the summary quality with Human and Imitation Edits.Through additional experiments, we show that SALT outperforms the conventional RLHF method (designed for human preferences) -DPO, when applied to human-edit data.We hope the evidence in our paper prompts researchers to explore, collect and better use different human feedback approaches scalably.

OBJECTIVE: Evictions are important social and behavioral determinants of health. Evictions are associated with a cascade of negative events that can lead to unemployment, housing insecurity/homelessness, long-term poverty, and mental health problems. In this study, we developed a natural language processing system to automatically detect eviction status from electronic health record (EHR) notes. MATERIALS AND METHODS: We first defined eviction status (eviction presence and eviction period) and then annotated eviction status in 5000 EHR notes from the Veterans Health Administration (VHA). We developed a novel model, KIRESH, that has shown to substantially outperform other state-of-the-art models such as fine-tuning pretrained language models like BioBERT and Bio_ClinicalBERT. Moreover, we designed a novel prompt to further improve the model performance by using the intrinsic connection between the 2 subtasks of eviction presence and period prediction. Finally, we used the Temperature Scaling-based Calibration on our KIRESH-Prompt method to avoid overconfidence issues arising from the imbalance dataset. RESULTS: KIRESH-Prompt substantially outperformed strong baseline models including fine-tuning the Bio_ClinicalBERT model to achieve 0.74672 MCC, 0.71153 Macro-F1, and 0.83396 Micro-F1 in predicting eviction period and 0.66827 MCC, 0.62734 Macro-F1, and 0.7863 Micro-F1 in predicting eviction presence. We also conducted additional experiments on a benchmark social determinants of health (SBDH) dataset to demonstrate the generalizability of our methods. CONCLUSION AND FUTURE WORK: KIRESH-Prompt has substantially improved eviction status classification. We plan to deploy KIRESH-Prompt to the VHA EHRs as an eviction surveillance system to help address the US Veterans' housing insecurity.

Abstract A patient portal allows discharged patients to access their personalized discharge instructions in electronic health records (EHRs). However, many patients have difficulty understanding or memorizing their discharge instructions (Zhao et al., 2017). In this paper, we present PaniniQA, a patient-centric interactive question answering system designed to help patients understand their discharge instructions. PaniniQA first identifies important clinical content from patients’ discharge instructions and then formulates patient-specific educational questions. In addition, PaniniQA is also equipped with answer verification functionality to provide timely feedback to correct patients’ misunderstandings. Our comprehensive automatic & human evaluation results demonstrate our PaniniQA is capable of improving patients’ mastery of their medical instructions through effective interactions.1

This paper proposes a new natural language processing (NLP) application for identifying medical jargon terms potentially difficult for patients to comprehend from electronic health record (EHR) notes.We first present a novel and publicly available dataset with expertannotated medical jargon terms from 18K+ EHR note sentences (M edJ).Then, we introduce a novel medical jargon extraction (M edJEx) model which has been shown to outperform existing state-of-the-art NLP models.First, MedJEx improved the overall performance when it was trained on an auxiliary Wikipedia hyperlink span dataset, where hyperlink spans provide additional Wikipedia articles to explain the spans (or terms), and then fine-tuned on the annotated MedJ data.Secondly, we found that a contextualized masked language model score was beneficial for detecting domain-specific unfamiliar jargon terms.Moreover, our results show that training on the auxiliary Wikipedia hyperlink span datasets improved six out of eight biomedical named entity recognition benchmark datasets.MedJEx is publicly available 1 .

Models pre-trained on large-scale regular text corpora often do not work well for user-generated data where the language styles differ significantly from the mainstream text. Here we present Context-Aware Rule Injection (CARI), an innovative method for formality style transfer (FST). CARI injects multiple rules into an end-to-end BERT-based encoder and decoder model. It learns to select optimal rules based on context. The intrinsic evaluation showed that CARI achieved the new highest performance on the FST benchmark dataset. Our extrinsic evaluation showed that CARI can greatly improve the regular pre-trained models' performance on several tweet sentiment analysis tasks.

Knowledge bases are critical to many applications. However, they are greatly incomplete. Enriching knowledge bases with new entities and new location attributes becomes increasingly important. Given a named entity with tweets and Web documents where the entity appears, we aim to predict the entity city-level location combining the geographical location knowledge embedded in both Twitter and Web. This task is helpful for knowledge base enrichment and tweet location prediction. In this paper we propose NELPTW, the first unsupervised framework forNamedEntityLocationPrediction by leveraging the knowledge fromTwitter andWeb. Based on each data source, NELPTW utilizes a linear function ranking model to generate several rankings to the candidate location set for each entity. To combine the knowledge from two sources which have different reliability and importance for the location prediction, an unsupervised rank aggregation algorithm is developed to aggregate multiple rankings for each entity to obtain a better ranking. A learning algorithm based on the EM method is proposed to automatically learn the parameters of the ranking model without requiring any training labels. The experimental results over a real world Twitter and Web data set show that our framework significantly outperforms the baselines in terms of accuracy.