Xuguang Ai

Yan Wang, Xuguang Ai, Jaisal Patel et al.

Structured financial audit verification is difficult for language-model agents because correctness depends on structured evidence rather than text alone. A model must link reported facts to taxonomy concepts, traverse calculation or dimensional relations, and recompute expected values before applying an audit rule. We propose AuditFlow, a graph-grounded multi-agent framework that separates adaptive search from deterministic verification. AuditFlow builds a symbolic environment from a static US-GAAP taxonomy graph and a dynamic XBRL filing graph, and exposes it through typed tools for fact retrieval, taxonomy traversal, numerical checking, and rule evaluation. Two junior auditors inspect each case from regulatory and evidentiary views, while a senior auditor resolves disagreements and can request further investigation. The final reports are fused through evidential aggregation to produce an audit verdict, expected value, evidence trail, and trustworthiness score. On a FinAuditing-derived FinMR sample, AuditFlow reaches 82.09% joint audit accuracy under GPT-5.5, outperforming the strongest baseline by 14.93 points. Removing deterministic checks drops accuracy to 17.91%, showing that the symbolic environment performs the verification step that the model cannot reliably replace.

Aidan Gilson, Xuguang Ai, Thilaka Arunachalam et al.

Despite the potential of Large Language Models (LLMs) in medicine, they may generate responses lacking supporting evidence or based on hallucinated evidence. While Retrieval Augment Generation (RAG) is popular to address this issue, few studies implemented and evaluated RAG in downstream domain-specific applications. We developed a RAG pipeline with 70,000 ophthalmology-specific documents that retrieve relevant documents to augment LLMs during inference time. In a case study on long-form consumer health questions, we systematically evaluated the responses including over 500 references of LLMs with and without RAG on 100 questions with 10 healthcare professionals. The evaluation focuses on factuality of evidence, selection and ranking of evidence, attribution of evidence, and answer accuracy and completeness. LLMs without RAG provided 252 references in total. Of which, 45.3% hallucinated, 34.1% consisted of minor errors, and 20.6% were correct. In contrast, LLMs with RAG significantly improved accuracy (54.5% being correct) and reduced error rates (18.8% with minor hallucinations and 26.7% with errors). 62.5% of the top 10 documents retrieved by RAG were selected as the top references in the LLM response, with an average ranking of 4.9. The use of RAG also improved evidence attribution (increasing from 1.85 to 2.49 on a 5-point scale, P<0.001), albeit with slight decreases in accuracy (from 3.52 to 3.23, P=0.03) and completeness (from 3.47 to 3.27, P=0.17). The results demonstrate that LLMs frequently exhibited hallucinated and erroneous evidence in the responses, raising concerns for downstream applications in the medical domain. RAG substantially reduced the proportion of such evidence but encountered challenges.

Zhenyue Qin, Younjoon Chung, Elijah Lee et al.

Vision impairment affects millions globally, and early detection is critical to preventing irreversible vision loss. Ophthalmology workflows require clinicians to integrate medical images, structured clinical data, and free-text notes to determine disease severity and management, which is time-consuming and burdensome. Recent multimodal large language models (MLLMs) show promise, but existing general and medical MLLMs perform poorly in ophthalmology, and few ophthalmology-specific MLLMs are openly available. We present VOLMO (Versatile and Open Large Models for Ophthalmology), a model-agnostic, data-open framework for developing ophthalmology-specific MLLMs. VOLMO includes three stages: ophthalmology knowledge pretraining on 86,965 image-text pairs from 26,569 articles across 82 journals; domain task fine-tuning on 26,929 annotated instances spanning 12 eye conditions for disease screening and severity classification; and multi-step clinical reasoning on 913 patient case reports for assessment, planning, and follow-up care. Using this framework, we trained a compact 2B-parameter MLLM and compared it with strong baselines, including InternVL-2B, LLaVA-Med-7B, MedGemma-4B, MedGemma-27B, and RETFound. We evaluated these models on image description generation, disease screening and staging classification, and assessment-and-management generation, with additional manual review by two healthcare professionals and external validation on three independent cohorts for age-related macular degeneration and diabetic retinopathy. Across settings, VOLMO-2B consistently outperformed baselines, achieving stronger image description performance, an average F1 of 87.4% across 12 eye conditions, and higher scores in external validation.

Shashank Gupta, Xuguang Ai, Ramakanth Kavuluru

End-to-end relation extraction (E2ERE) is an important and realistic application of natural language processing (NLP) in biomedicine. In this paper, we aim to compare three prevailing paradigms for E2ERE using a complex dataset focused on rare diseases involving discontinuous and nested entities. We use the RareDis information extraction dataset to evaluate three competing approaches (for E2ERE): NER $\rightarrow$ RE pipelines, joint sequence to sequence models, and generative pre-trained transformer (GPT) models. We use comparable state-of-the-art models and best practices for each of these approaches and conduct error analyses to assess their failure modes. Our findings reveal that pipeline models are still the best, while sequence-to-sequence models are not far behind; GPT models with eight times as many parameters are worse than even sequence-to-sequence models and lose to pipeline models by over 10 F1 points. Partial matches and discontinuous entities caused many NER errors contributing to lower overall E2E performances. We also verify these findings on a second E2ERE dataset for chemical-protein interactions. Although generative LM-based methods are more suitable for zero-shot settings, when training data is available, our results show that it is better to work with more conventional models trained and tailored for E2ERE. More innovative methods are needed to marry the best of the both worlds from smaller encoder-decoder pipeline models and the larger GPT models to improve E2ERE. As of now, we see that well designed pipeline models offer substantial performance gains at a lower cost and carbon footprint for E2ERE. Our contribution is also the first to conduct E2ERE for the RareDis dataset.

Xuguang Ai, Ramakanth Kavuluru

End-to-end relation extraction (E2ERE) is an important task in information extraction, more so for biomedicine as scientific literature continues to grow exponentially. E2ERE typically involves identifying entities (or named entity recognition (NER)) and associated relations, while most RE tasks simply assume that the entities are provided upfront and end up performing relation classification. E2ERE is inherently more difficult than RE alone given the potential snowball effect of errors from NER leading to more errors in RE. A complex dataset in biomedical E2ERE is the ChemProt dataset (BioCreative VI, 2017) that identifies relations between chemical compounds and genes/proteins in scientific literature. ChemProt is included in all recent biomedical natural language processing benchmarks including BLUE, BLURB, and BigBio. However, its treatment in these benchmarks and in other separate efforts is typically not end-to-end, with few exceptions. In this effort, we employ a span-based pipeline approach to produce a new state-of-the-art E2ERE performance on the ChemProt dataset, resulting in $> 4\%$ improvement in F1-score over the prior best effort. Our results indicate that a straightforward fine-grained tokenization scheme helps span-based approaches excel in E2ERE, especially with regards to handling complex named entities. Our error analysis also identifies a few key failure modes in E2ERE for ChemProt.

Anran Li, Yuanyuan Chen, Wenjun Long et al.

Large language models (LLMs) have demonstrated strong performance on medical benchmarks, including question answering and diagnosis. To enable their use in clinical settings, LLMs are typically further adapted through continued pretraining or post-training using clinical data. However, most medical LLMs are trained on data from a single institution, which faces limitations in generalizability and safety in heterogeneous systems. Federated learning (FL) is a promising solution for enabling collaborative model development across healthcare institutions. Yet applying FL to LLMs in medicine remains fundamentally limited. First, conventional FL requires transmitting the full model during each communication round, which becomes impractical for multi-billion-parameter LLMs given the limited computational resources. Second, many FL algorithms implicitly assume data homogeneity, whereas real-world clinical data are highly heterogeneous across patients, diseases, and institutional practices. We introduce the model-agnostic and parameter-efficient federated learning framework for adapting LLMs to medical applications. Fed-MedLoRA transmits only low-rank adapter parameters, reducing communication and computation overhead, while Fed-MedLoRA+ further incorporates adaptive, data-aware aggregation to improve convergence under cross-site heterogeneity. We apply the framework to clinical information extraction (IE), which transforms patient narratives into structured medical entities and relations. Accuracy was assessed across five patient cohorts through comparisons with BERT models, and LLaMA-3 and DeepSeek-R1, GPT-4o models. Evaluation settings included (1) in-domain training and testing, (2) external validation on independent cohorts, and (3) a low-resource new-site adaptation scenario using real-world clinical notes from the Yale New Haven Health System.

Roy Jiang, Hyunjae Kim, Zhenyue Qin et al.

Multimodal large language models (MLLMs) have demonstrated promise on publicly available dermatology benchmarks. However, benchmark performance may not generalize to real-world dermatologic decision-making. To quantify this benchmark-to-bedside gap, we evaluated four open-weight MLLMs (InternVL-Chat v1.5, LLaVA-Med v1.5, SkinGPT4 and MedGemma-4B-Instruct) and one commercial MLLM (GPT-4.1) across three publicly available dermatology datasets and a retrospective multi-site hospital-based dermatology consultation cohort comprising 5,811 cases and 46,405 clinical images. Models were evaluated on two clinically relevant tasks: differential diagnosis generation and severity-based triage. Diagnostic performance was modest on public datasets and declined substantially in the real-world cohort. On public benchmarks, top-3 diagnostic accuracy reached 26.55% for the best open-weight model and 42.25% for GPT-4.1. On real-world consultation cases using images alone, top-3 diagnostic accuracy fell to 1.50%-13.35% among open-weight models and 24.65% for GPT-4.1. Incorporating clinical context improved performance across all models, increasing top-3 diagnostic accuracy up to 28.75% among open-weight models and 38.93% for GPT-4.1. However, model outputs were highly sensitive to incomplete or erroneous consultation context. For severity-based triage, models achieved moderate sensitivity (above 60%), suggesting potential utility for screening but insufficient reliability for clinical deployment. These findings demonstrate that benchmark performance substantially overestimates the real-world clinical capability of current dermatology MLLMs.

Lingfei Qian, Mauro Giuffre, Yan Wang et al.

Clinical decision-making increasingly relies on timely and context-aware access to patient information within Electronic Health Records (EHRs), yet most existing natural language question-answering (QA) systems are evaluated solely on benchmark datasets, limiting their practical relevance. To overcome this limitation, we introduce EHRNavigator, a multi-agent framework that harnesses AI agents to perform patient-level question answering across heterogeneous and multimodal EHR data. We assessed its performance using both public benchmark and institutional datasets under realistic hospital conditions characterized by diverse schemas, temporal reasoning demands, and multimodal evidence integration. Through quantitative evaluation and clinician-validated chart review, EHRNavigator demonstrated strong generalization, achieving 86% accuracy on real-world cases while maintaining clinically acceptable response times. Overall, these findings confirm that EHRNavigator effectively bridges the gap between benchmark evaluation and clinical deployment, offering a robust, adaptive, and efficient solution for real-world EHR question answering.

Xueqing Peng, Zhuohan Xie, Yupeng Cao et al.

As AI agents improve, the central question is no longer whether they can solve isolated well-defined financial tasks, but whether they can reliably carry out financial professional work. Existing financial benchmarks offer only a partial view of this ability, as they primarily evaluate static competencies such as question answering, retrieval, summarization, and classification. We introduce Herculean, the first skilled benchmark for agentic financial intelligence spanning four representative workflows, including Trading, Hedging, Market Insights, and Auditing. Each workflow is instantiated as a standardized MCP-based skill environment with its own tools, interaction dynamics, constraints, and success criteria, enabling consistent end-to-end assessment of heterogeneous agent systems. Across frontier agents, we find agents perform relatively well on Trading and Market Insights, but struggle substantially on Hedging and Auditing, where long-horizon coordination, state consistency, and structured verification are critical. Overall, our results point to a key gap in current agents in turning financial reasoning into dependable workflow execution in high-stakes financial workflows.

Aviv Brokman, Xuguang Ai, Yuhang Jiang et al.

Objective: Zero-shot methodology promises to cut down on costs of dataset annotation and domain expertise needed to make use of NLP. Generative large language models trained to align with human goals have achieved high zero-shot performance across a wide variety of tasks. As of yet, it is unclear how well these models perform on biomedical relation extraction (RE). To address this knowledge gap, we explore patterns in the performance of OpenAI LLMs across a diverse sampling of RE tasks. Methods: We use OpenAI GPT-4-turbo and OpenAI's reasoning models o1 and GPT-OSS to conduct end-to-end RE experiments on seven datasets. We use the JSON generation capabilities of GPT models to generate structured output in two ways: (1) by defining an explicit schema describing the structure of relations, and (2) using a setting that infers the structure from the prompt language. Results: Our work is the first to study and compare the performance of the GPT-4, o1 and GPT-OSS for the end-to-end zero-shot biomedical RE task across a broad array of datasets. We found the zero-shot performances to be proximal to that of fine-tuned methods. The limitations of this approach are that it performs poorly on instances containing many relations and errs on the boundaries of textual mentions. Conclusion: LLMs exhibit promising zero-shot capabilities in complex biomedical RE tasks, offering competitive performance with reduced dataset curation costs and NLP modeling needs but with increased perpetual compute costs. Addressing the limitations we identify could further boost reliability. The code, data, and prompts for all our experiments are publicly available for additional benchmarking by the community: https://github.com/bionlproc/ZeroShotRE

Qingyu Chen, Yan Hu, Xueqing Peng et al.

The rapid growth of biomedical literature poses challenges for manual knowledge curation and synthesis. Biomedical Natural Language Processing (BioNLP) automates the process. While Large Language Models (LLMs) have shown promise in general domains, their effectiveness in BioNLP tasks remains unclear due to limited benchmarks and practical guidelines. We perform a systematic evaluation of four LLMs, GPT and LLaMA representatives on 12 BioNLP benchmarks across six applications. We compare their zero-shot, few-shot, and fine-tuning performance with traditional fine-tuning of BERT or BART models. We examine inconsistencies, missing information, hallucinations, and perform cost analysis. Here we show that traditional fine-tuning outperforms zero or few shot LLMs in most tasks. However, closed-source LLMs like GPT-4 excel in reasoning-related tasks such as medical question answering. Open source LLMs still require fine-tuning to close performance gaps. We find issues like missing information and hallucinations in LLM outputs. These results offer practical insights for applying LLMs in BioNLP.

Sahana Srinivasan, Xuguang Ai, Minjie Zou et al.

Question: What is the performance and reasoning ability of OpenAI o1 compared to other large language models in addressing ophthalmology-specific questions? Findings: This study evaluated OpenAI o1 and five LLMs using 6,990 ophthalmological questions from MedMCQA. O1 achieved the highest accuracy (0.88) and macro-F1 score but ranked third in reasoning capabilities based on text-generation metrics. Across subtopics, o1 ranked first in ``Lens'' and ``Glaucoma'' but second to GPT-4o in ``Corneal and External Diseases'', ``Vitreous and Retina'' and ``Oculoplastic and Orbital Diseases''. Subgroup analyses showed o1 performed better on queries with longer ground truth explanations. Meaning: O1's reasoning enhancements may not fully extend to ophthalmology, underscoring the need for domain-specific refinements to optimize performance in specialized fields like ophthalmology.

Minjie Zou, Sahana Srinivasan, Thaddaeus Wai Soon Lo et al.

Recent advances in reasoning-focused large language models (LLMs) mark a shift from general LLMs toward models designed for complex decision-making, a crucial aspect in medicine. However, their performance in specialized domains like ophthalmology remains underexplored. This study comprehensively evaluated and compared the accuracy and reasoning capabilities of four newly developed reasoning-focused LLMs, namely DeepSeek-R1, OpenAI o1, o3-mini, and Gemini 2.0 Flash-Thinking. Each model was assessed using 5,888 multiple-choice ophthalmology exam questions from the MedMCQA dataset in zero-shot setting. Quantitative evaluation included accuracy, Macro-F1, and five text-generation metrics (ROUGE-L, METEOR, BERTScore, BARTScore, and AlignScore), computed against ground-truth reasonings. Average inference time was recorded for a subset of 100 randomly selected questions. Additionally, two board-certified ophthalmologists qualitatively assessed clarity, completeness, and reasoning structure of responses to differential diagnosis questions.O1 (0.902) and DeepSeek-R1 (0.888) achieved the highest accuracy, with o1 also leading in Macro-F1 (0.900). The performance of models across the text-generation metrics varied: O3-mini excelled in ROUGE-L (0.151), o1 in METEOR (0.232), DeepSeek-R1 and o3-mini tied for BERTScore (0.673), DeepSeek-R1 (-4.105) and Gemini 2.0 Flash-Thinking (-4.127) performed best in BARTScore, while o3-mini (0.181) and o1 (0.176) led AlignScore. Inference time across the models varied, with DeepSeek-R1 being slowest (40.4 seconds) and Gemini 2.0 Flash-Thinking fastest (6.7 seconds). Qualitative evaluation revealed that DeepSeek-R1 and Gemini 2.0 Flash-Thinking tended to provide detailed and comprehensive intermediate reasoning, whereas o1 and o3-mini displayed concise and summarized justifications.

Anran Li, Lingfei Qian, Mengmeng Du et al.

Large Language Models (LLMs) have demonstrated significant potential in medicine. To date, LLMs have been widely applied to tasks such as diagnostic assistance, medical question answering, and clinical information synthesis. However, a key open question remains: to what extent do LLMs memorize medical training data. In this study, we present the first comprehensive evaluation of memorization of LLMs in medicine, assessing its prevalence (how frequently it occurs), characteristics (what is memorized), volume (how much content is memorized), and potential downstream impacts (how memorization may affect medical applications). We systematically analyze common adaptation scenarios: (1) continued pretraining on medical corpora, (2) fine-tuning on standard medical benchmarks, and (3) fine-tuning on real-world clinical data, including over 13,000 unique inpatient records from Yale New Haven Health System. The results demonstrate that memorization is prevalent across all adaptation scenarios and significantly higher than reported in the general domain. Memorization affects both the development and adoption of LLMs in medicine and can be categorized into three types: beneficial (e.g., accurate recall of clinical guidelines and biomedical references), uninformative (e.g., repeated disclaimers or templated medical document language), and harmful (e.g., regeneration of dataset-specific or sensitive clinical content). Based on these findings, we offer practical recommendations to facilitate beneficial memorization that enhances domain-specific reasoning and factual accuracy, minimize uninformative memorization to promote deeper learning beyond surface-level patterns, and mitigate harmful memorization to prevent the leakage of sensitive or identifiable patient information.

Sahana Srinivasan, Xuguang Ai, Thaddaeus Wai Soon Lo et al.

Current benchmarks evaluating large language models (LLMs) in ophthalmology are limited in scope and disproportionately prioritise accuracy. We introduce BELO (BEnchmarking LLMs for Ophthalmology), a standardized and comprehensive evaluation benchmark developed through multiple rounds of expert checking by 13 ophthalmologists. BELO assesses ophthalmology-related clinical accuracy and reasoning quality. Using keyword matching and a fine-tuned PubMedBERT model, we curated ophthalmology-specific multiple-choice-questions (MCQs) from diverse medical datasets (BCSC, MedMCQA, MedQA, BioASQ, and PubMedQA). The dataset underwent multiple rounds of expert checking. Duplicate and substandard questions were systematically removed. Ten ophthalmologists refined the explanations of each MCQ's correct answer. This was further adjudicated by three senior ophthalmologists. To illustrate BELO's utility, we evaluated six LLMs (OpenAI o1, o3-mini, GPT-4o, DeepSeek-R1, Llama-3-8B, and Gemini 1.5 Pro) using accuracy, macro-F1, and five text-generation metrics (ROUGE-L, BERTScore, BARTScore, METEOR, and AlignScore). In a further evaluation involving human experts, two ophthalmologists qualitatively reviewed 50 randomly selected outputs for accuracy, comprehensiveness, and completeness. BELO consists of 900 high-quality, expert-reviewed questions aggregated from five sources: BCSC (260), BioASQ (10), MedMCQA (572), MedQA (40), and PubMedQA (18). A public leaderboard has been established to promote transparent evaluation and reporting. Importantly, the BELO dataset will remain a hold-out, evaluation-only benchmark to ensure fair and reproducible comparisons of future models.