arXiv subjects

Yanjun Gao

Publications and source records attributed to Yanjun Gao.

At least 19 recordsLinked to original sources

arXiv2026

Surgical Alignment in Knowledge Graph Training for Clinical Diagnosis with Large Language Models

Biomedical knowledge graphs (KGs) offer structured medical knowledge that can ground large language model (LLM) reasoning in clinical diagnosis application, yet how KG signal should be integrated into LLMs remains an open question. We present a systematic study spanning five KG task formulations, three training paradigms, two KGs, and three base LLMs. At the task level, all paradigms improve over the non-finetuned baseline, but methods with comparable in-domain accuracy show substantially different knowledge transfer behavior. We introduce Gradient Intervention Density (GID) and Gradient Distortion (GD) to measure how broadly an optimizer modifies the pretrained model. GID and GD together reveal a clear divide: KG-judgment training under KL regularization produces sparse, localized updates (a regime we term as surgical alignment), while task-specific SFT produces dense ones. A controlled ablation shows that the objective and KL contribute to sparsity independently, and the paradigms that produce sparse updates also improve reasoning quality, even when their in-domain accuracy is lower than task-specific SFT. Assessing KG-LLM integration thus requires complementing accuracy with optimization-geometry diagnostics. Our implementation can be found at https://github.com/LARK-NLP-Lab/Surgical-Alignment.

cs.CL↗

arXiv2026

RoboSynChallenge: Mastering Real-World Dexterity via Generalizing Synthesized Manipulation Skills

Achieving generalizable robotic manipulation remains a central challenge in embodied intelligence. Despite rapid advances in model architectures and learning algorithms, progress is often limited by the scarcity and narrow diversity of real-world data. The RoboSynChallenge competition introduces a unified benchmark to evaluate and advance the generalizability of manipulation policies across a spectrum of tasks, environments, and difficulty levels. To alleviate the shortage of realistic data, the challenge integrates large-scale synthetic data generation with standardized real-world robotic evaluation. Participants are encouraged to leverage synthesized state-action trials to improve general-purpose policy learning, while final assessments are conducted exclusively on unseen real-world manipulation environments. Baseline implementations, including Transformer-, Diffusion-, Vision-Language-Action, and World-Action-Model-based policies, are provided to ensure reproducibility and comparability. By coupling scalable simulation-based training with rigorous real-world validation, RoboSynChallenge aims to foster the development of broadly capable, data-efficient, and adaptable manipulation systems, thereby paving the way toward truly general robotic intelligence.

cs.RO↗

arXiv2026

LogosKG: Hardware-Optimized Scalable and Interpretable Knowledge Graph Retrieval

Knowledge graphs (KGs) are increasingly integrated with large language models (LLMs) to provide structured, verifiable reasoning. A core operation in this integration is multi-hop retrieval, yet existing systems struggle to balance efficiency, scalability, and interpretability. We introduce LogosKG, a novel, hardware-aligned framework that enables scalable and interpretable k-hop retrieval on large KGs by building on symbolic KG formulations and executing traversal as hardware-efficient operations over decomposed subject, object, and relation representations. To scale to billion-edge graphs, LogosKG integrates degree-aware partitioning, cross-graph routing, and on-demand caching. Experiments show substantial efficiency gains over CPU and GPU baselines without loss of retrieval fidelity. With proven performance in KG retrieval, a downstream two-round KG-LLM interaction demonstrates how LogosKG enables large-scale, evidence-grounded analysis of how KG topology, such as hop distribution and connectivity, shapes the alignment between structured biomedical knowledge and LLM diagnostic reasoning, thereby opening the door for next-generation KG-LLM integration. The source code is publicly available at https://github.com/LARK-NLP-Lab/LogosKG, and an online demo is available at https://lark-nlp-lab-logoskg.hf.space/.

cs.CL↗

arXiv2026

CLSGen: A Dual-Head Fine-Tuning Framework for Joint Probabilistic Classification and Verbalized Explanation

With the recent progress of Large Language Models (LLMs), there is a growing interest in applying these models to solve complex and challenging problems. Modern LLMs, capable of processing long contexts and generating verbalized explanations, offer significant potential in addressing real-world applications. However, a critical hurdle in deploying LLMs for practical decision-making is their inability to provide reliable, quantitative probabilities. While task-specific fine-tuning of LLMs using traditional discriminative objectives (similar to encoder-only models) can yield probability estimates, this often leads to catastrophic forgetting and linguistic collapse. Consequently, the model loses its ability to generate explanations, severely undermining its interpretability and usability. To address this challenge, we propose CLSGen, a novel LLM fine-tuning framework designed for binary classification tasks. The CLSGen framework encompasses a new model architecture, training methodology, and data construction strategy to enable robust probability estimation without sacrificing the model's inherent explanation-generation capabilities. Experimental results across multiple benchmark datasets demonstrate that models fine-tuned with CLSGen outperform existing baselines in classification metrics (AUROC and F1-score). Regarding explanation, the results showed strong alignment between predicted labels and generated justifications, as well as high readability.

cs.CL↗

arXiv2026

Tracing the Latent Threads: A Mechanistic Study of How LLMs Represent and Operationalize Race and Ethnicity Cues

Large language models (LLMs) increasingly operate in high-stakes settings where demographic attributes such as race and ethnicity may be explicitly stated or implicitly suggested through textual cues. However, existing studies primarily document outcome-level disparities, offering limited insight into internal mechanisms underlying these effects. We present a mechanistic study of how race and ethnicity cues are represented and operationalized within LLMs. Using two publicly available datasets spanning toxicity-related generation and clinical narrative understanding tasks, we analyze three open-source models with a reproducible interpretability pipeline combining probing, neuron-level attribution, and targeted intervention. We find that sensitivity to demographic cues is distributed across internal units and varies substantially across models. These units often align with entangled semantic facets, including explicit group labels, geography, language, culture, and associations related to stereotypes. Interventions on selected units can change some biased prediction patterns, but substantial residual effects remain, suggesting that effective mitigation requires understanding distributed, task-specific mechanisms rather than manipulating a small set of identified neurons alone. Code: https://github.com/LARK-NLP-Lab/LLM-Bias-Interpretability.

cs.CL↗

arXiv2025

Experimental Realization of All-Optical Terahertz Attoclock

The attoclock is a powerful tool for probing ultrafast electron dynamics with attosecond precision.Here, we demonstrate an all-optical terahertz (THz) attoclock that reconstructs photoionization dynamics by detecting the THz radiation emitted from Ar atoms ionized by two-color (800 nm/400 nm) laser fields. In this approach, the polarization direction of the emitted THz field reflects the direction of the photoelectron drift velocity and thus serves as a direct observable that encodes the effective ionization delay, analogous to the angular deflection of photoelectrons in conventional attoclocks. By precisely tailoring the relative phase and ellipticity of the driving fields, we observe intensity-dependent rotations of the THz polarization. These rotations, which reveal changes of the effective delay, are consistent with both conventional attoclock measurements and time-dependent Schr\"odinger equation simulations. Our experiment establishes the feasibility of the THz attoclock as a vacuum-free and contactless probe of tunneling dynamics, offering a transformative alternative for investigating condensed-matter systems where photoelectron detection is challenging.

physics.optics↗

arXiv2025

Large language models management of medications: three performance analyses

Purpose: Large language models (LLMs) have proven performance for certain diagnostic tasks, however limited studies have evaluated their consistency in recommending appropriate medication regimens for a given diagnosis. Medication management is a complex task that requires synthesis of drug formulation and complete order instructions for safe use. Here, the performance of GPT 4o, an LLM available with ChatGPT, was tested for three medication management tasks. Methods: GPT-4o performance was tested using three medication tasks: identifying available formulations for a given generic drug name, identifying drug-drug interactions (DDI) for a given medication regimen, and preparing a medication order for a given generic drug name. For each experiment, the models raw text response was captured exactly as returned and evaluated using clinician evaluation in addition to standard LLM metrics, including Term Frequency-Inverse Document Frequency (TF IDF) vectors, normalized Levenshtein similarity, and Recall-Oriented Understudy for Gisting Evaluation (ROUGE 1/ROUGE L F1) between each response and its reference string. Results: For the first task of drug-formulation matching, GPT-4o had 49% accuracy for generic medications being matched to all available formulations, with an average of 1.23 omissions per medication and 1.14 hallucinations per medication. For the second task of drug-drug interaction identification, the accuracy was 54.7% for identifying the DDI pair. For the third task, GPT-4o generated order sentences containing no medication or abbreviation errors in 65.8% of cases. Conclusions: Model performance for basic medication tasks was consistently poor. This evaluation highlights the need for domain-specific training through clinician-annotated datasets and a comprehensive evaluation framework for benchmarking performance.

cs.CL↗

arXiv2025

Brittleness and Promise: Knowledge Graph Based Reward Modeling for Diagnostic Reasoning

Large language models (LLMs) show promise for diagnostic reasoning but often lack reliable, knowledge grounded inference. Knowledge graphs (KGs), such as the Unified Medical Language System (UMLS), offer structured biomedical knowledge that can support trustworthy reasoning. Prior approaches typically integrate KGs via retrieval augmented generation or fine tuning, inserting KG content into prompts rather than enabling structured reasoning. We explore an alternative paradigm: treating the LLM as a reward model of KG reasoning paths, where the model learns to judge whether a candidate path leads to correct diagnosis for a given patient input. This approach is inspired by recent work that leverages reward training to enhance model reasoning abilities, and grounded in computational theory, which suggests that verifying a solution is often easier than generating one from scratch. It also parallels physicians' diagnostic assessment, where they judge which sequences of findings and intermediate conditions most plausibly support a diagnosis. We first systematically evaluate five task formulation for knowledge path judging and eight training paradigm. Second, we test whether the path judging abilities generalize to downstream diagnostic tasks, including diagnosis summarization and medical question answering. Experiments with three open source instruct-tuned LLMs reveal both promise and brittleness: while specific reward optimization and distillation lead to strong path-judging performance, the transferability to downstream tasks remain weak. Our finding provides the first systematic assessment of "reward model style" reasoning over clinical KGs, offering insights into how structured, reward-based supervision influences diagnostic reasoning in GenAI systems for healthcare.

cs.CL↗

arXiv2025

Evaluating Retrieval-Augmented Generation vs. Long-Context Input for Clinical Reasoning over EHRs

Objective: To evaluate whether retrieval-augmented generation (RAG) can serve as an efficient alternative to long-context prompting for clinical reasoning over electronic health records (EHRs). Methods: We defined three EHR-based tasks that are replicable across health systems and vary in reasoning complexity: 1) extracting imaging procedures (modality, date, and anatomic site), 2) generating timelines of therapeutic antibiotic use, and 3) identifying the key diagnoses for a hospitalization. Using real inpatient clinical notes from a US academic health system, we evaluated three large language models (GPT-5.4-mini, Mistral Medium 3, DeepSeek V3.1) with varying amounts of provided context, comparing targeted retrieval to using the most recent clinical notes. Results: For Imaging Procedures, RAG strongly outperformed recent-note inputs and exceeded long-context performance (by 0.17-9.83 F1 across all models) using fewer than 8K tokens. Similar benefits were observed for Antibiotic Timelines, where <8K of retrieved tokens matched long-context recent-notes performance (between -3.26 to +3.24 Jaccard). Error analysis revealed that missing information in the clinical notes--often due to inter-hospital transfers--limited performance to some extent. However, performance on the Diagnosis Generation task remains largely static across methods and models. Discussion: RAG demonstrated strong token efficiency across tasks, with the clearest and most consistent gains observed for imaging extraction and antibiotic timeline reconstruction. Diagnosis generation proved the most challenging task, suggesting ceiling effects imposed by documentation variability and evaluation constraints. Conclusion: Our results suggest that RAG remains a competitive and efficient approach for clinical tasks over large amounts of EHR, even as newer models become capable of handling increasingly longer amounts of text.

cs.CL↗

arXiv2025

Simple Yet Effective: An Information-Theoretic Approach to Multi-LLM Uncertainty Quantification

Large language models (LLMs) often behave inconsistently across inputs, indicating uncertainty and motivating the need for its quantification in high-stakes settings. Prior work on calibration and uncertainty quantification often focuses on individual models, overlooking the potential of model diversity. We hypothesize that LLMs make complementary predictions due to differences in training and the Zipfian nature of language, and that aggregating their outputs leads to more reliable uncertainty estimates. To leverage this, we propose MUSE (Multi-LLM Uncertainty via Subset Ensembles), a simple information-theoretic method that uses Jensen-Shannon Divergence to identify and aggregate well-calibrated subsets of LLMs. Experiments on binary prediction tasks demonstrate improved calibration and predictive performance compared to single-model and na\"ive ensemble baselines. In addition, we explore using MUSE as guided signals with chain-of-thought distillation to fine-tune LLMs for calibration. MUSE is available at:https://github.com/LARK-NLP-Lab/MUSE.

cs.LG↗

arXiv2025

Uncovering Hidden Violent Tendencies in LLMs: A Demographic Analysis via Behavioral Vignettes

Large language models (LLMs) are increasingly proposed for detecting and responding to violent content online, yet their ability to reason about morally ambiguous, real-world scenarios remains underexamined. We present the first study to evaluate LLMs using a validated social science instrument designed to measure human response to everyday conflict, namely the Violent Behavior Vignette Questionnaire (VBVQ). To assess potential bias, we introduce persona-based prompting that varies race, age, and geographic identity within the United States. Six LLMs developed across different geopolitical and organizational contexts are evaluated under a unified zero-shot setting. Our study reveals two key findings: (1) LLMs surface-level text generation often diverges from their internal preference for violent responses; (2) their violent tendencies vary across demographics, frequently contradicting established findings in criminology, social science, and psychology.

cs.CL↗

arXiv2025

Attributing Response to Context: A Jensen-Shannon Divergence Driven Mechanistic Study of Context Attribution in Retrieval-Augmented Generation

Retrieval-Augmented Generation (RAG) leverages large language models (LLMs) combined with external contexts to enhance the accuracy and reliability of generated responses. However, reliably attributing generated content to specific context segments, context attribution, remains challenging due to the computationally intensive nature of current methods, which often require extensive fine-tuning or human annotation. In this work, we introduce a novel Jensen-Shannon Divergence driven method to Attribute Response to Context (ARC-JSD), enabling efficient and accurate identification of essential context sentences without additional fine-tuning, gradient-calculation or surrogate modelling. Evaluations on a wide range of RAG benchmarks, such as TyDi QA, Hotpot QA, and Musique, using instruction-tuned LLMs in different scales demonstrate superior accuracy and significant computational efficiency improvements compared to the previous surrogate-based method. Furthermore, our mechanistic analysis reveals specific attention heads and multilayer perceptron (MLP) layers responsible for context attribution, providing valuable insights into the internal workings of RAG models and how they affect RAG behaviours. Our code is available at https://github.com/ruizheliUOA/ARC_JSD.

cs.CL↗

arXiv2025

"It Felt Like I Was Left in the Dark": Exploring Information Needs and Design Opportunities for Family Caregivers of Older Adult Patients in Critical Care Settings

Older adult patients constitute a rapidly growing subgroup of Intensive Care Unit (ICU) patients. In these situations, their family caregivers are expected to represent the unconscious patients to access and interpret patients' medical information. However, caregivers currently have to rely on overloaded clinicians for information updates and typically lack the health literacy to understand complex medical information. Our project aims to explore the information needs of caregivers of ICU older adult patients, from which we can propose design opportunities to guide future AI systems. The project begins with formative interviews with 11 caregivers to identify their challenges in accessing and interpreting medical information; From these findings, we then synthesize design requirements and propose an AI system prototype to cope with caregivers' challenges. The system prototype has two key features: a timeline visualization to show the AI extracted and summarized older adult patients' key medical events; and an LLM-based chatbot to provide context-aware informational support. We conclude our paper by reporting on the follow-up user evaluation of the system and discussing future AI-based systems for ICU caregivers of older adults.

cs.HC↗

arXiv2025

Large Language Models with Temporal Reasoning for Longitudinal Clinical Summarization and Prediction

Recent advances in large language models (LLMs) have shown potential in clinical text summarization, but their ability to handle long patient trajectories with multi-modal data spread across time remains underexplored. This study systematically evaluates several state-of-the-art open-source LLMs, their Retrieval Augmented Generation (RAG) variants and chain-of-thought (CoT) prompting on long-context clinical summarization and prediction. We examine their ability to synthesize structured and unstructured Electronic Health Records (EHR) data while reasoning over temporal coherence, by re-engineering existing tasks, including discharge summarization and diagnosis prediction from two publicly available EHR datasets. Our results indicate that long context windows improve input integration but do not consistently enhance clinical reasoning, and LLMs are still struggling with temporal progression and rare disease prediction. While RAG shows improvements in hallucination in some cases, it does not fully address these limitations. Our work fills the gap in long clinical text summarization, establishing a foundation for evaluating LLMs with multi-modal data and temporal reasoning.

cs.CL↗

arXiv2025

Development and Validation of the Provider Documentation Summarization Quality Instrument for Large Language Models

As Large Language Models (LLMs) are integrated into electronic health record (EHR) workflows, validated instruments are essential to evaluate their performance before implementation. Existing instruments for provider documentation quality are often unsuitable for the complexities of LLM-generated text and lack validation on real-world data. The Provider Documentation Summarization Quality Instrument (PDSQI-9) was developed to evaluate LLM-generated clinical summaries. Multi-document summaries were generated from real-world EHR data across multiple specialties using several LLMs (GPT-4o, Mixtral 8x7b, and Llama 3-8b). Validation included Pearson correlation for substantive validity, factor analysis and Cronbach's alpha for structural validity, inter-rater reliability (ICC and Krippendorff's alpha) for generalizability, a semi-Delphi process for content validity, and comparisons of high-versus low-quality summaries for discriminant validity. Seven physician raters evaluated 779 summaries and answered 8,329 questions, achieving over 80% power for inter-rater reliability. The PDSQI-9 demonstrated strong internal consistency (Cronbach's alpha = 0.879; 95% CI: 0.867-0.891) and high inter-rater reliability (ICC = 0.867; 95% CI: 0.867-0.868), supporting structural validity and generalizability. Factor analysis identified a 4-factor model explaining 58% of the variance, representing organization, clarity, accuracy, and utility. Substantive validity was supported by correlations between note length and scores for Succinct (rho = -0.200, p = 0.029) and Organized ($\rho = -0.190$, $p = 0.037$). Discriminant validity distinguished high- from low-quality summaries ($p < 0.001$). The PDSQI-9 demonstrates robust construct validity, supporting its use in clinical practice to evaluate LLM-generated summaries and facilitate safer integration of LLMs into healthcare workflows.

cs.AI↗

arXiv2024

Position Paper On Diagnostic Uncertainty Estimation from Large Language Models: Next-Word Probability Is Not Pre-test Probability

Large language models (LLMs) are being explored for diagnostic decision support, yet their ability to estimate pre-test probabilities, vital for clinical decision-making, remains limited. This study evaluates two LLMs, Mistral-7B and Llama3-70B, using structured electronic health record data on three diagnosis tasks. We examined three current methods of extracting LLM probability estimations and revealed their limitations. We aim to highlight the need for improved techniques in LLM confidence estimation.

cs.AI↗

arXiv2024

Bridging Knowledge Gaps in Clinical AI: An Activity Theory Perspective on Interdisciplinary Data Work for Telehealth

Advanced AI technologies are increasingly integrated into clinical domains to advance patient care. The design and development of clinical AI technologies necessitate seamless collaboration between clinical and technical experts. However, such interdisciplinary teams are often unsuccessful, with a lack of systematic analysis of collaboration barriers and coping strategies. This work examines two clinical AI collaborations in the context of speech-language pathology via semi-structured interviews with six clinical and seven technical experts. Using Activity Theory (AT) as our analytical lens, we examine persistent knowledge gaps and collaboration tensions across clinical and technical workflows, and show how clinical data can function as boundary objects while interdisciplinary collaborators may act as knowledge brokers to help address these challenges. Our findings contribute to CSCW research on interdisciplinary teams' data work by showing how shared clinical data, boundary objects, and broker roles shape coordination in early-stage clinical AI collaboration, and by providing insights into best practices for future collaboration.

cs.HC↗

arXiv2024

Evaluation of Large Language Models for Summarization Tasks in the Medical Domain: A Narrative Review

Large Language Models have advanced clinical Natural Language Generation, creating opportunities to manage the volume of medical text. However, the high-stakes nature of medicine requires reliable evaluation, which remains a challenge. In this narrative review, we assess the current evaluation state for clinical summarization tasks and propose future directions to address the resource constraints of expert human evaluation.

cs.CL↗