Author name cluster

Yue Shen

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

8 papers

1 author row

AAAI Conference 2026 Conference Paper

MedLA: A Logic-Driven Multi-Agent Framework for Complex Medical Reasoning with Large Language Models

Siqi Ma
Jiajie Huang
Fan Zhang
Jinlin Wu
Yue Shen
Guohui Fan
Zhu Zhang
Zelin Zang

Answering complex medical questions requires not only domain expertise and patient-specific information, but also structured and multi-perspective reasoning. Existing multi-agent approaches often rely on fixed roles or shallow interaction prompts, limiting their ability to detect and resolve fine-grained logical inconsistencies. To address this, we propose MedLA, a logic-driven multi-agent framework built on large language models. Each agent organizes its reasoning process into an explicit logical tree based on syllogistic triads (major premise, minor premise, and conclusion), enabling transparent inference and premise-level alignment. Agents engage in a multi-round, graph-guided discussion to compare and iteratively refine their logic trees, achieving consensus through error correction and contradiction resolution. We demonstrate that MedLA consistently outperforms both static role-based systems and single-agent baselines on challenging benchmarks such as MedDDx and standard medical QA tasks. Furthermore, MedLA scales effectively across both open-source and commercial LLM backbones, achieving state-of-the-art performance and offering a generalizable paradigm for trustworthy medical reasoning.

PDF Details DOI

AAAI Conference 2026 Conference Paper

PRGB Benchmark: A Robust Placeholder-Assisted Algorithm for Benchmarking Retrieval-Augmented Generation

Zhehao Tan
Yihan Jiao
Dan Yang
Junwei Liu
Lei Liu
Jie Feng
Duolin Sun
Yue Shen

Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by integrating external knowledge, where the LLM's ability to generate responses based on the combination of a given query and retrieved documents is crucial. However, most benchmarks focus on overall RAG system performance, rarely assessing LLM-specific capabilities. Current benchmarks emphasize broad aspects such as noise robustness, but lack a systematic and granular evaluation framework on document utilization. To this end, we introduce Placeholder-RAG-Benchmark, a multi-level fine-grained benchmark, emphasizing the following progressive dimensions: (1) multi-level filtering abilities, (2) combination abilities, and (3) reference reasoning. To provide a more nuanced understanding of LLMs' roles in RAG systems, we formulate an innovative placeholder-based approach to decouple the contributions of the LLM's parametric knowledge and the external knowledge. Experiments demonstrate the limitations of representative LLMs in the RAG system's generation capabilities, particularly in error resilience and context faithfulness. Our benchmark provides a reproducible framework for developing more reliable and efficient RAG systems.

PDF Details DOI

AIIM Journal 2025 Journal Article

CATI: A medical context-enhanced framework for diagnosis code assignment in the UK Biobank study

Yue Shen
Jie Wang
Zhe Wang
Zhihao Shi
Hanzhu Chen
Zheng Wang
Yukang Jiang
Xiaopu Wang

Diagnosis codes are standard code format of diseases or medical conditions. This study is aimed at assigning diagnosis codes to patients in large-scale biobanks, particularly addressing the issue of missing codes for some patients. This is crucial for downstream disease-related tasks. While recent methods primarily rely on structured biobank data for code assignment, they often overlook the valuable medical context provided by textual information in the biobanks and hierarchical structure of the disease coding system. To address this gap, we have developed CATI, a medical context-enhanced framework for diagnosis Code Assignment by integrating Textual details derived from key features and disease hIerarchy. The study is based on the UK Biobank data and considers Phecodes and ICD-10 codes as standard disease formats. We start by representing ten informative codified features using their formal names and then integrate them into CATI as text embeddings, achieved through prompt tuning on the pre-trained language model BioBERT. Recognizing the hierarchical structure of diagnosis codes, we have developed a novel convolution layer in our method that effectively propagates logits between adjacent diagnosis codes. Evaluation results demonstrate that CATI outperforms existing state-of-the-art methods in terms of both Phecodes and ICD-10 codes, boasting at least a 5. 16% improvement in average AUROC for unseen disease codes and an 8. 68% rise in average AUPRC for disease codes with training instances ranging in (1000, 10000]. This framework contributes to the formation of well-defined cohorts for downstream studies and offers a unique perspective for addressing complex healthcare tasks by incorporating vital medical context.

Details DOI

EAAI Journal 2025 Journal Article

Improving the magnetic resonance images super-resolution with a dual-channel enhancement model incorporating complementary information

Chunqiao He
Hang Liu
Yue Shen
Deyin Zhou
Lin Wu
Hailin Ma
Tao Zhang

Although significant progress has been made in image super-resolution using artificial intelligence, achieving high-quality super-resolution for magnetic resonance (MR) images remains challenging due to their unique imaging principles and processes. Inspired by MR parallel imaging, we propose a novel concept to improve the MR image super-resolution quality by leveraging the complementary spatial information inherently contained in multi-channel receive coils. A new MR image degradation model was developed to generate the training dataset that complies with the parallel imaging and Sensitivity Encoding (SENSE) reconstruction. A dual-channel enhancement model, named sensitivity encoding based super-resolution (SenseSR), is then devised with the main channel processing the single low-resolution image and the enhancement channel processing the multiple images from each coil channel. SenseSR is mainly featured with cascaded double enhancement blocks that can extract deeper features of the multiple coil-channel images and fuse them together into the main channel. Experiments were performed to test the performance and compare it with other benchmark models. The results demonstrate a significant improvement in MR image super-resolution quality, with an enhancement of peak signal-to-noise ratio ranging from 0. 5 to 6. 5 decibels (dB). Further experiments with different testing datasets and MR images collected in-situ demonstrated that SenseSR also has good generalization capability and robustness, indicating its potential for clinical applications. The code is available at https: //github. com/MISR-Lab/SenseSR.

Details DOI

JBHI Journal 2024 Journal Article

Eye Gaze Guided Cross-Modal Alignment Network for Radiology Report Generation

Peixi Peng
Wanshu Fan
Yue Shen
Wenfei Liu
Xin Yang
Qiang Zhang
Xiaopeng Wei
Dongsheng Zhou

The potential benefits of automatic radiology report generation, such as reducing misdiagnosis rates and enhancing clinical diagnosis efficiency, are significant. However, existing data-driven methods lack essential medical prior knowledge, which hampers their performance. Moreover, establishing global correspondences between radiology images and related reports, while achieving local alignments between images correlated with prior knowledge and text, remains a challenging task. To address these shortcomings, we introduce a novel Eye Gaze Guided Cross-modal Alignment Network (EGGCA-Net) for generating accurate medical reports. Our approach incorporates prior knowledge from radiologists' Eye Gaze Region (EGR) to refine the fidelity and comprehensibility of report generation. Specifically, we design a Dual Fine-Grained Branch (DFGB) and a Multi-Task Branch (MTB) to collaboratively ensure the alignment of visual and textual semantics across multiple levels. To establish fine-grained alignment between EGR-related images and sentences, we introduce the Sentence Fine-grained Prototype Module (SFPM) within DFGB to capture cross-modal information at different levels. Additionally, to learn the alignment of EGR-related image topics, we introduce the Multi-task Feature Fusion Module (MFFM) within MTB to refine the encoder output information. Finally, a specifically designed label matching mechanism is designed to generate reports that are consistent with the anticipated disease states. The experimental outcomes indicate that the introduced methodology surpasses previous advanced techniques, yielding enhanced performance on two extensively used benchmark datasets: Open-i and MIMIC-CXR.

Details DOI

AAAI Conference 2024 Conference Paper

LLMRG: Improving Recommendations through Large Language Model Reasoning Graphs

Yan Wang
Zhixuan Chu
Xin Ouyang
Simeng Wang
Hongyan Hao
Yue Shen
Jinjie Gu
Siqiao Xue

Recommendation systems aim to provide users with relevant suggestions, but often lack interpretability and fail to capture higher-level semantic relationships between user behaviors and profiles. In this paper, we propose a novel approach that leverages large language models (LLMs) to construct personalized reasoning graphs. These graphs link a user's profile and behavioral sequences through causal and logical inferences, representing the user's interests in an interpretable way. Our approach, LLM reasoning graphs (LLMRG), has four components: chained graph reasoning, divergent extension, self-verification and scoring, and knowledge base self-improvement. The resulting reasoning graph is encoded using graph neural networks, which serves as additional input to improve conventional recommender systems, without requiring extra user or item information. Our approach demonstrates how LLMs can enable more logical and interpretable recommender systems through personalized reasoning graphs. LLMRG allows recommendations to benefit from both engineered recommendation systems and LLM-derived reasoning graphs. We demonstrate the effectiveness of LLMRG on benchmarks and real-world scenarios in enhancing base recommendation models.

PDF Details DOI

EAAI Journal 2023 Journal Article

An online path planning algorithm for autonomous marine geomorphological surveys based on AUV

Yixiao Zhang
Qi Wang
Yue Shen
Bo He

This paper proposed a data-driven bi-pattern (DDBP) path planning algorithm for ocean geomorphological surveys based on Autonomous Underwater Vehicles (AUVs). When an AUV conducts surveys in unknown areas, it uses the observation data of real-time side-scan sonar to conduct environment modeling to drive independent online path re-planning (PRP) according to the feature density of the interesting targets. Based on the DDBP algorithm, the AUV can autonomously focus on regions with rich target distribution and deviate from regions with sparse target distribution without prior knowledge of the task region. The quality and efficiency of the AUV-based surveys can be improved by focusing on the underwater detection area with high feature density. The DDBP algorithm includes two patterns: rough and fine scan, and the corresponding planning pattern is selected according to the distribution of the detected targets. AUV performs online PRP in the corresponding pattern according to the pre-identified strategy set. We conducted simulation experiments and selected sand waves and fish reefs as natural and artificial structures to conduct typical marine survey tests. Compared with the traditional marine survey method, the survey efficiency was increased by 33. 6% and 29. 6%, respectively, in the two DDBP survey experiments for sand waves; the efficiency increased by 32. 9% and 36. 7%, respectively, in the two groups of DDBP survey experiments on artificial reefs. The proposed general technical framework for online path planning driven by real-time observation data has good application prospects in underwater archaeology, rapid understanding of specific targets on the seafloor, and search of specific targets.

Details DOI

IJCAI Conference 2021 Conference Paper

User Retention: A Causal Approach with Triple Task Modeling

Yang Zhang
Dong Wang
Qiang Li
Yue Shen
Ziqi Liu
Xiaodong Zeng
Zhiqiang Zhang
Jinjie Gu

For many Internet companies, it has been an important focus to improve user retention rate. To achieve this goal, we need to recommend proper services in order to meet the demands of users. Unlike conventional click-through rate (CTR) estimation, there are lots of noise in the collected data when modeling retention, caused by two major issues: 1) implicit impression-revisit effect: users could revisit the APP even if they do not explicitly interact with the recommender system; 2) selection bias: recommender system suffers from selection bias caused by user's self-selection. To address the above challenges, we propose a novel method named UR-IPW (User Retention Modeling with Inverse Propensity Weighting), which 1) makes full use of both explicit and implicit interactions in the observed data. 2) models revisit rate estimation from a causal perspective accounting for the selection bias problem. The experiments on both offline and online environments from different scenarios demonstrate the superiority of UR-IPW over previous methods. To the best of our knowledge, this is the first work to model user retention by estimating the revisit rate from a causal perspective.

PDF Details DOI