arXiv subjects

Honghan Wu

Publications and source records attributed to Honghan Wu.

At least 19 recordsLinked to original sources

arXiv2026

Learning to Fuse LLMs with Ontology Rankers for Rare-Disease Diagnosis

Ontology rankers remain useful for rare-disease diagnosis because each candidate can be traced to matched patient phenotypes. Large language models (LLMs) can generate differential diagnoses from the same patient description, but their predictions lack an equally clear evidence trail. Rather than asking which system should replace the other, we ask whether an LLM can improve the ranker without giving up its evidence. Our behavior-based fusion model examines the two ranked lists, their agreement, and the ontology support behind each candidate, and learns how much to rely on each system for the individual case. Before comparison, we remove a documented test-set leakage pathway caused by benchmark cases and ontology annotations being derived from the same publications. Across eight open LLMs, fusion improves Phenomizer Recall@1 by 7.86 percentage points on Phenopacket Store and 20.18 points on RAMEDIS. When paired with DeepSeek-V4-Flash through an API, a fusion model trained only on the other LLMs improves Recall@1 from 0.1657 to 0.2176, a 5.19-point gain, without retraining. For 90.8% of correct fused diagnoses, the disease retains candidate-level ontology evidence that can be inspected. These results show that LLMs can strengthen an established diagnostic tool without discarding the structured evidence that makes it useful.

cs.CL↗

arXiv2026

One Score, Two Decisions: Selective Prediction on the Rare-Disease Tail

Given a patient's clinical findings, a diagnostic system ranks possible diseases and must decide when to endorse its first prediction or defer it for review. This decision is usually made by thresholding the top score. Selective prediction over ranked outputs begins with two checks. First, the ranker must produce enough correct top-ranked predictions to make the target feasible. Across 2,000 patient records stratified by disease prevalence, eight small open-weight LLMs achieve at most 4.6% Recall@1 on ultra-rare diseases. At 10% coverage, even a perfect confidence ranking of their existing predictions therefore cannot reach 50% selective accuracy. More accurate models pass the same check, showing that the limit is regime-specific. Second, the confidence signal must match the decision being made. For fixed-candidate rankers, the top-two margin cancels components shared across candidates. On phenotype-only Exomiser, it selects 10% of cases at 29.0% accuracy, compared with 13.3% overall, while the top score provides no reliable gate. Yet that cancellation can remove information needed to detect whether the candidate list contains an answer. SciFact retrieval and biomedical entity linking confirm this distinction. Finally, we prove that unlabelled scores alone cannot determine whether switching to the margin will help.

cs.LG↗

arXiv2026

Presentation, Not Mechanism: A Render Confound in Deprecation-Aware Memory Evaluation

AI systems increasingly retrieve from records that revise themselves: issue threads, encyclopedic histories, policy logs, and long conversations. The challenge is not only finding relevant evidence, but deciding which claims remain in force, which were superseded, and when to abstain. Structured memories promise to solve this with typed edges, temporal updates, and conflict status, yet evaluations often change mechanism and prompt presentation together. We study this as Evidence-State Revision, comparing flat retrieval, coarse edge invalidation, and fine-grained RevisionLedger on 2,907 high-agreement questions from GitHub, multi-repo issue histories, Wikipedia, and DyKnow-style temporal streams. A render-matched control (same layout, deprecation disabled) reveals the central confound: when a value is changed and later restored, RevisionLedger appears to beat a flat baseline by +0.182, but almost all the gain comes from easier presentation; the fine-grained mechanism residual is indistinguishable from zero (+0.021 to +0.025 across two judge families). After presentation is controlled, coarse invalidation is the only mechanism that pays for current-state queries, beating the fine ledger by 0.084; the same query-sufficiency principle says provenance mainly needs retained invalidated evidence, not richer typing. Memory evaluations should hold render fixed, and deprecation-aware systems should deploy the coarsest retained state that covers their queries.

cs.LG↗

arXiv2026

BioMedArena: An Open-source Toolkit for Building and Evaluating Biomedical Deep Research Agents

Reproducing and comparing deep research agents today is hard: the same backbone evaluated on the same benchmark can report different accuracies across papers because the harness and tool registry differ, and integrating a new model into a comparable evaluation surface costs weeks of model-specific engineering. These are symptoms of a broader reproducibility problem in deep research agent research. Here, we introduce BioMedArena, an open-source toolkit that addresses this reproducibility gap and provides an arena for comparing deep research agents under a shared evaluation environment. BioMedArena decouples six layers of biomedical agent evaluation -- benchmark loading, tool exposure, tool selection, harness mode, context management, and scoring -- and exposes 166 biomedical benchmarks and 75 biomedical tools across 9 functional families. Adding a new model, benchmark, or tool can be accomplished with a few-line provider adapter. Beyond evaluation infrastructure, BioMedArena ships a library of high-quality reference components: 6 agent harnesses (including our proposed Mutual-Evolve) and 6 context-management strategies, any of which can be equipped on any backbone. Equipping these components substantially improves all 12 backbones; on each of 8 representative biomedical benchmarks, the best equipped backbone surpasses prior state-of-the-art (SOTA), by 15.01 percentage points on average. The toolkit, configurations, and per-task traces are available at https://github.com/AI-in-Health/BioMedArena.

cs.AI↗

arXiv2026

A specialized reasoning large language model for accelerating rare disease diagnosis: a randomized AI physician assistance trial

Rare diseases affect millions of individuals worldwide, yet timely diagnosis remains a major public health challenge due to scarcity of specialized clinical expertise. While large language models (LLMs) show promise to support rare disease diagnosis, current models are constrained by insufficient clinical deployability, limited clinically grounded evidence, and scarcity of training data. Here we present RaDaR (Rare Disease navigatoR), an open-source, compact reasoning LLM (32B parameters) for rare disease diagnosis. RaDaR was trained with 49,170 publicly available free-text cases and 104,666 synthetic cases with reasoning-enhanced training. RaDaR showed the strongest performance among evaluated open-source models, including the 671B DeepSeek-R1, across public benchmarks and four external validation centers. In a retrospective cohort, RaDaR prioritized the final diagnosis before documented clinical suspicion in 61.06 percent of cases, corresponding to a potential lead time of 1.87 months and 50.18 percent of the within-center interval. In a randomized physician-assistance trial, RaDaR assistance improved physicians' rare-disease diagnostic accuracy by 21.44 percentage points compared with internet search alone. Synthetic-data ablations suggested that phenotype-anchored narratives provide useful training signal for long-tail rare diseases, with a monotonic scaling trend within the tested data range. Together, RaDaR and its development and validation framework provide a deployable rare-disease reasoning model and a reproducible development framework for diagnostic AI under data scarcity.

cs.AI↗

arXiv2026

Better Accuracies, Worse Reasoning: A Step-Level Audit of Medical Chain-of-Thought Distillation

Chain-of-thought (CoT) distillation trains a smaller model to imitate a teacher's reasoning trace, but it is typically evaluated by final-answer metrics including accuracy. We ask whether gains in answer quality are accompanied by improvements in the trace. In medical QA, where short answer options can leave a richer clinical justification under-specified, a Qwen3-8B student distilled from a DeepSeek-V3-family teacher improves on MedQA-USMLE answer metrics (SC@64 74.7% to 84.4%; expected calibration error (ECE) 0.096 to 0.034). Yet under a Kimi-K2.6 style-blind LLM-judge audit, its error rate over non-abstained steps rises from 30.6% to 50.3%. In this primary medical setting, answer quality and trace factuality move in opposite directions. This before--after pattern persists across evaluators, teacher strengths, student scales and families, medical benchmarks, and style, segmentation, and answer-correctness controls. A 150-step blinded audit by a clinical expert reproduces the same ordering. Boundary checks narrow the scope of the claim: the risk appears when a compact answer under-constrains the rationale and a capable student can imitate expert-like form without reliably grounding each local claim. Standard answer metrics and aggregate hedging rates do not reveal the shift. When such traces are released or reused, answer-level metrics alone are insufficient.

cs.AI↗

arXiv2026

Uncovering Latent Pathological Signatures in Pulmonary CT via Cross-Window Knowledge Distillation

Multi-window CT imaging captures complementary pathological information across anatomical structures of differing densities, yet existing deep learning methods fuse representations only at later stages, missing cross-density interactions. We propose a cross-window knowledge distillation framework in which student encoders learn latent clinical priors from a teacher trained on the most informative window. Evaluated retrospectively on three cohorts - COPD-CT-DF (n=719), RSNA PE (n=1,433), and an in-house CTEPD dataset (n=161) - distillation improved per-window AUC by 10.1-16.5 percentage points on COPD-CT-DF (0.75-0.81 to 0.90-0.94; all P<0.001), with ensemble AUC reaching 0.9960. Similar gains were observed on RSNA PE (0.80-0.83 to 0.90-0.92) and CTEPD (AUC 0.7481 vs. 0.6264). Cross-window distillation internalises pathological signatures invisible to supervised approaches, offering a generalisable solution for multi-window pulmonary CT analysis.

eess.IV↗

arXiv2026

HH-SAE: Discovering and Steering Hierarchical Knowledge of Complex Manifolds

Rare semantic innovations in high-dimensional, mission-critical domains are often obscured by dense background contexts, a challenge we define as \textit{feature density conflict}. We introduce the \textbf{Hybrid Hierarchical SAE (HH-SAE)} to resolve this by factorizing manifolds into a nested hierarchy of \textbf{Contextual} ($L_0$), \textbf{Atomic} ($f_1$), and \textbf{Compository} ($f_2$) tiers. Evaluating across disparate manifolds, HH-SAE demonstrates superior resolution by \textbf{``fracturing'' administrative clinical labels into physiological modes} and achieving a peak \textbf{cross-domain zero-shot AUC of 0.9156 in fraud detection}. Path ablation confirms the architecture's structural necessity, revealing a 13.46\% utility collapse when contextual subtraction is removed. Finally, knowledge-steered synthesis achieves a +9.9\% AUPRC lift over state-of-the-art generators, proving that HH-SAE effectively prioritizes high-order mechanistic innovation over environmental proxies to enable high-precision discovery in high-stakes environments.

cs.LG↗

arXiv2026

A Regime Theory of Controller Class Selection for LLM Action Decisions

Deployed language and vision-language models must decide, on each input, whether to answer directly, retrieve evidence, defer to a stronger model, or abstain. Contrary to the common monotonicity intuition, greater per-input expressivity is not uniformly beneficial in finite samples: under identical strict cross-validation, different benchmarks prefer different controller classes. This reflects a finite-sample limitation of instance-level uncertainty signals, which can be exhausted at a distribution-dependent scale. We organize controllers into a nested lattice of four classes: fixed actions, partition routers, instance-level controllers, and prior-gated controllers, ordered by complexity. We prove a regime theory that turns three data-estimable bottlenecks into a class choice: how much improvement is possible beyond the best fixed action, whether there are enough samples for instance-level controllers to make reliable decisions, and how much improvement a coarse partition router can recover when instance-level signal is unreliable. The resulting Bernstein-tight threshold has a matching information-theoretic lower bound, and strict nested cross-validation provably selects a near-best class. Across SMS-Spam, HallusionBench, A-OKVQA, and FOLIO, the predicted class matches the empirical winner; the prior-gated controller wins on TextVQA when OCR tokens supply a label-free prediction-time prior. Code is available at https://github.com/Anonymous-Awesome-Submissions/Regime-Theory.

cs.AI↗

arXiv2026

LoV3D: Grounding Cognitive Prognosis Reasoning in Longitudinal 3D Brain MRI via Regional Volume Assessments

Longitudinal brain MRI is essential for characterizing the progression of neurological diseases such as Alzheimer's disease assessment. However, current deep-learning tools fragment this process: classifiers reduce a scan to a label, volumetric pipelines produce uninterpreted measurements, and vision-language models (VLMs) may generate fluent but potentially hallucinated conclusions. We present LoV3D, a pipeline for training 3D vision-language models, which reads longitudinal T1-weighted brain MRI, produces a region-level anatomical assessment, conducts longitudinal comparison with the prior scan, and finally outputs a three-class diagnosis (Cognitively Normal, Mild Cognitive Impairment, or Dementia) along with a synthesized diagnostic summary. The stepped pipeline grounds the final diagnosis by enforcing label consistency, longitudinal coherence, and biological plausibility, thereby reducing the risks of hallucinations. The training process introduces a clinically-weighted Verifier that scores candidate outputs automatically against normative references derived from standardized volume metrics, driving Direct Preference Optimization without a single human annotation. On a subject-level held-out ADNI test set (479 scans, 258 subjects), LoV3D achieves 93.7% three-class diagnostic accuracy (+34.8% over the no-grounding baseline), 97.2% on two-class diagnosis accuracy (+4% over the SOTA) and 82.6% region-level anatomical classification accuracy (+33.1% over VLM baselines). Zero-shot transfer yields 95.4% on MIRIAD (100% Dementia recall) and 82.9% three-class accuracy on AIBL, confirming high generalizability across sites, scanners, and populations. Code is available at https://github.com/Anonymous-TEVC/LoV-3D.

cs.CV↗

arXiv2026

RiskAgent: Synergizing Language Models with Validated Tools for Evidence-Based Risk Prediction

Large Language Models (LLMs) achieve competitive results compared to human experts in medical examinations. However, it remains a challenge to apply LLMs to complex clinical decision-making, which requires a deep understanding of medical knowledge and differs from the standardized, exam-style scenarios commonly used in current efforts. A common approach is to fine-tune LLMs for target tasks, which, however, not only requires substantial data and computational resources but also remains prone to generating `hallucinations'. In this work, we present RiskAgent, which synergizes language models with hundreds of validated clinical decision tools supported by evidence-based medicine, to provide generalizable and faithful recommendations. Our experiments show that RiskAgent not only achieves superior performance on a broad range of clinical risk predictions across diverse scenarios and diseases, but also demonstrates robust generalization in tool learning on the external MedCalc-Bench dataset, as well as in medical reasoning and question answering on three representative benchmarks, MedQA, MedMCQA, and MMLU.

cs.LG↗

arXiv2025

Error Correction in Radiology Reports: A Knowledge Distillation-Based Multi-Stage Framework

The increasing complexity and workload of clinical radiology leads to inevitable oversights and mistakes in their use as diagnostic tools, causing delayed treatments and sometimes life-threatening harm to patients. While large language models (LLMs) have shown remarkable progress in many tasks, their utilities in detecting and correcting errors in radiology reporting are limited. This paper proposes a novel dual-knowledge infusion framework that enhances LLMs' capability for radiology report proofreading through systematic integration of medical expertise. Specifically, the knowledge infusion combines medical knowledge graph distillation (MKGD) with external knowledge retrieval (EXKR), enabling an effective automated approach in tackling mistakes in radiology reporting. By decomposing the complex proofreading task into three specialized stages of detection, localization, and correction, our method mirrors the systematic review process employed by expert radiologists, ensuring both precision and clinical interpretability. To perform a robust, clinically relevant evaluation, a comprehensive benchmark is also proposed using real-world radiology reports with real-world error patterns, including speech recognition confusions, terminology ambiguities, and template-related inconsistencies. Extensive evaluations across multiple LLM architectures demonstrate substantial improvements of our approach: up to 31.56% increase in error detection accuracy and 37.4% reduction in processing time. Human evaluation by radiologists confirms superior clinical relevance and factual consistency compared to existing approaches.

cs.CL↗

arXiv2025

Graph-based LLM over Semi-Structured Population Data for Dynamic Policy Response

Timely and accurate analysis of population-level data is crucial for effective decision-making during public health emergencies such as the COVID-19 pandemic. However, the massive input of semi-structured data, including structured demographic information and unstructured human feedback, poses significant challenges to conventional analysis methods. Manual expert-driven assessments, though accurate, are inefficient, while standard NLP pipelines often require large task-specific labeled datasets and struggle with generalization across diverse domains. To address these challenges, we propose a novel graph-based reasoning framework that integrates large language models with structured demographic attributes and unstructured public feedback in a weakly supervised pipeline. The proposed approach dynamically models evolving citizen needs into a need-aware graph, enabling population-specific analyses based on key features such as age, gender, and the Index of Multiple Deprivation. It generates interpretable insights to inform responsive health policy decision-making. We test our method using a real-world dataset, and preliminary experimental results demonstrate its feasibility. This approach offers a scalable solution for intelligent population health monitoring in resource-constrained clinical and governmental settings.

cs.AI↗

arXiv2025

Towards deployment-centric multimodal AI beyond vision and language

Multimodal artificial intelligence (AI) integrates diverse types of data via machine learning to improve understanding, prediction, and decision-making across disciplines such as healthcare, science, and engineering. However, most multimodal AI advances focus on models for vision and language data, while their deployability remains a key challenge. We advocate a deployment-centric workflow that incorporates deployment constraints early to reduce the likelihood of undeployable solutions, complementing data-centric and model-centric approaches. We also emphasise deeper integration across multiple levels of multimodality and multidisciplinary collaboration to significantly broaden the research scope beyond vision and language. To facilitate this approach, we identify common multimodal-AI-specific challenges shared across disciplines and examine three real-world use cases: pandemic response, self-driving car design, and climate change adaptation, drawing expertise from healthcare, social science, engineering, science, sustainability, and finance. By fostering multidisciplinary dialogue and open research practices, our community can accelerate deployment-centric development for broad societal impact.

cs.AI↗

arXiv2025

HARE: an entity and relation centric evaluation framework for histopathology reports

Medical domain automated text generation is an active area of research and development; however, evaluating the clinical quality of generated reports remains a challenge, especially in instances where domain-specific metrics are lacking, e.g. histopathology. We propose HARE (Histopathology Automated Report Evaluation), a novel entity and relation centric framework, composed of a benchmark dataset, a named entity recognition (NER) model, a relation extraction (RE) model, and a novel metric, which prioritizes clinically relevant content by aligning critical histopathology entities and relations between reference and generated reports. To develop the HARE benchmark, we annotated 813 de-identified clinical diagnostic histopathology reports and 652 histopathology reports from The Cancer Genome Atlas (TCGA) with domain-specific entities and relations. We fine-tuned GatorTronS, a domain-adapted language model to develop HARE-NER and HARE-RE which achieved the highest overall F1-score (0.915) among the tested models. The proposed HARE metric outperformed traditional metrics including ROUGE and Meteor, as well as radiology metrics such as RadGraph-XL, with the highest correlation and the best regression to expert evaluations (higher than the second best method, GREEN, a large language model based radiology report evaluator, by Pearson $r = 0.168$, Spearman $ρ= 0.161$, Kendall $τ= 0.123$, $R^2 = 0.176$, $RMSE = 0.018$). We release HARE, datasets, and the models at https://github.com/knowlab/HARE to foster advancements in histopathology report generation, providing a robust framework for improving the quality of reports.

cs.CL↗

arXiv2025

RadEyeVideo: Enhancing general-domain Large Vision Language Model for chest X-ray analysis with video representations of eye gaze

Large Vision-Language Models (LVLMs) have demonstrated promising performance in chest X-ray (CXR) analysis. To enhance human-computer interaction, several studies have incorporated radiologists' eye gaze, typically through heatmaps or textual prompts. However, these methods often overlook the sequential order of eye movements, which could provide valuable insights by highlighting both the areas of interest and the order in which they are examined. In this work, we propose a novel approach called RadEyeVideo that integrates radiologists' eye-fixation data as a video sequence, capturing both the temporal and spatial dynamics of their gaze. We evaluate this method in CXR report generation and disease diagnosis using three general-domain, open-source LVLMs with video input capabilities. When prompted with eye-gaze videos, model performance improves by up to 24.6% in the report generation task and on average 15.2% for both tasks using scaled evaluation metrics. Notably, RadEyeVideo enhanced an open-domain LVLM model, LLaVA-OneVision, to surpass task-specific medical LVLMs such as MAIRA-2 and CheXagent, trained on large Chest X-ray data. This work highlights that domain expert's knowledge (eye-gaze information in this case), when effectively integrated with LVLMs, can significantly enhance general-domain models' capabilities in clinical tasks. RadEyeVideo is a step toward a scalable human-centered approach of utilizing LVLMs in medical image analytics.

cs.CV↗

arXiv2025

Adverse Event Extraction from Discharge Summaries: A New Dataset, Annotation Scheme, and Initial Findings

In this work, we present a manually annotated corpus for Adverse Event (AE) extraction from discharge summaries of elderly patients, a population often underrepresented in clinical NLP resources. The dataset includes 14 clinically significant AEs-such as falls, delirium, and intracranial haemorrhage, along with contextual attributes like negation, diagnosis type, and in-hospital occurrence. Uniquely, the annotation schema supports both discontinuous and overlapping entities, addressing challenges rarely tackled in prior work. We evaluate multiple models using FlairNLP across three annotation granularities: fine-grained, coarse-grained, and coarse-grained with negation. While transformer-based models (e.g., BERT-cased) achieve strong performance on document-level coarse-grained extraction (F1 = 0.943), performance drops notably for fine-grained entity-level tasks (e.g., F1 = 0.675), particularly for rare events and complex attributes. These results demonstrate that despite high-level scores, significant challenges remain in detecting underrepresented AEs and capturing nuanced clinical language. Developed within a Trusted Research Environment (TRE), the dataset is available upon request via DataLoch and serves as a robust benchmark for evaluating AE extraction methods and supporting future cross-dataset generalisation.

cs.CL↗

arXiv2025

BioHopR: A Benchmark for Multi-Hop, Multi-Answer Reasoning in Biomedical Domain

Biomedical reasoning often requires traversing interconnected relationships across entities such as drugs, diseases, and proteins. Despite the increasing prominence of large language models (LLMs), existing benchmarks lack the ability to evaluate multi-hop reasoning in the biomedical domain, particularly for queries involving one-to-many and many-to-many relationships. This gap leaves the critical challenges of biomedical multi-hop reasoning underexplored. To address this, we introduce BioHopR, a novel benchmark designed to evaluate multi-hop, multi-answer reasoning in structured biomedical knowledge graphs. Built from the comprehensive PrimeKG, BioHopR includes 1-hop and 2-hop reasoning tasks that reflect real-world biomedical complexities. Evaluations of state-of-the-art models reveal that O3-mini, a proprietary reasoning-focused model, achieves 37.93% precision on 1-hop tasks and 14.57% on 2-hop tasks, outperforming proprietary models such as GPT4O and open-source biomedical models including HuatuoGPT-o1-70B and Llama-3.3-70B. However, all models exhibit significant declines in multi-hop performance, underscoring the challenges of resolving implicit reasoning steps in the biomedical domain. By addressing the lack of benchmarks for multi-hop reasoning in biomedical domain, BioHopR sets a new standard for evaluating reasoning capabilities and highlights critical gaps between proprietary and open-source models while paving the way for future advancements in biomedical LLMs.

cs.CL↗