Tong Ruan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Tong Ruan has a total of 162 co-authors. Here are the top co-authors by number of shared publications:
- Jingping Liu
School of Information Science and Engineering, East China University of Science and Technology, Shanghai, 200237, China
13 shared publications Yongqi Fan
East China University of Science and Technology Shanghai China
8 shared publicationsQi Ye
School of Information Science and Engineering East China University of Science and Technology Shanghai China
7 shared publicationsJiacheng Wang
6 shared publicationsHaofen Wang
Tongji University
5 shared publications- Weiyan Zhang
School of Information Science and Engineering, East China University of Science and Technology, Shanghai, China
5 shared publications
Latest Publications
- 9 July 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 332
MV-MoE: A Multi-View Mixture-of-Expert Tuning Method for Medical LLMs
- 9 July 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 332
MV-MoE: A Multi-View Mixture-of-Expert Tuning Method for Medical LLMs
- 7 April 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 322
MARM: Medical adaptive reasoning model
- 7 April 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 322
MARM: Medical adaptive reasoning model
- Open Access
PsychēChat: An Empathic Framework Focused on Emotion Shift Tracking and Safety Risk Analysis in Psychological Counseling
Large language models (LLMs) have demonstrated notable advancements in psychological counseling. However, existing models generally do not explicitly model seekers' emotion shifts across counseling sessions, a core focus in classical psychological schools. Moreover, how to align counselor models' responses with these emotion shifts while proactively mitigating safety risks remains underexplored. To bridge these gaps, we propose PsychēChat, which explicitly integrates emotion shift tracking and safety risk analysis for psychological counseling. Specifically, we employ interactive role-playing to synthesize counselor--seeker dialogues, incorporating two modules: Emotion Management Module, to capture seekers' current emotions and emotion shifts; and Risk Control Module, to anticipate seekers' subsequent reactions and identify potential risks. Furthermore, we introduce two modeling paradigms. The Agent Mode structures emotion management, risk control, and counselor responses into a collaborative multi-agent pipeline. The LLM Mode integrates these stages into a unified chain-of-thought for end-to-end inference, balancing efficiency and performance. Extensive experiments, including interactive scoring, dialogue-level evaluation, and human assessment, demonstrate that PsychēChat outperforms existing methods for emotional insight and safety control.
Open AccessPsychēChat: An Empathic Framework Focused on Emotion Shift Tracking and Safety Risk Analysis in Psychological Counseling
Large language models (LLMs) have demonstrated notable advancements in psychological counseling. However, existing models generally do not explicitly model seekers' emotion shifts across counseling sessions, a core focus in classical psychological schools. Moreover, how to align counselor models' responses with these emotion shifts while proactively mitigating safety risks remains underexplored. To bridge these gaps, we propose PsychēChat, which explicitly integrates emotion shift tracking and safety risk analysis for psychological counseling. Specifically, we employ interactive role-playing to synthesize counselor--seeker dialogues, incorporating two modules: Emotion Management Module, to capture seekers' current emotions and emotion shifts; and Risk Control Module, to anticipate seekers' subsequent reactions and identify potential risks. Furthermore, we introduce two modeling paradigms. The Agent Mode structures emotion management, risk control, and counselor responses into a collaborative multi-agent pipeline. The LLM Mode integrates these stages into a unified chain-of-thought for end-to-end inference, balancing efficiency and performance. Extensive experiments, including interactive scoring, dialogue-level evaluation, and human assessment, demonstrate that PsychēChat outperforms existing methods for emotional insight and safety control.
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 4942-4951
I2CR: Intra- and Inter-modal Collaborative Reflections for Multimodal Entity Linking
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 4942-4951
Open AccessI2CR: Intra- and Inter-modal Collaborative Reflections for Multimodal Entity Linking
- 13 October 2025
- Published by Elsevier in Neural Networks
- Vol. 195, 108203
VLExpan: A visual-enhanced LLM framework with inductive and deductive policies for entity set expansion
- 13 October 2025
- Published by Elsevier in Neural Networks
- Vol. 195, 108203
VLExpan: A visual-enhanced LLM framework with inductive and deductive policies for entity set expansion
- Open Access
LCDS: A Logic-Controlled Discharge Summary Generation System Supporting Source Attribution and Expert Review
Despite the remarkable performance of Large Language Models (LLMs) in automated discharge summary generation, they still suffer from hallucination issues, such as generating inaccurate content or fabricating information without valid sources. In addition, electronic medical records (EMRs) typically consist of long-form data, making it challenging for LLMs to attribute the generated content to the sources. To address these challenges, we propose LCDS, a Logic-Controlled Discharge Summary generation system. LCDS constructs a source mapping table by calculating textual similarity between EMRs and discharge summaries to constrain the scope of summarized content. Moreover, LCDS incorporates a comprehensive set of logical rules, enabling it to generate more reliable silver discharge summaries tailored to different clinical fields. Furthermore, LCDS supports source attribution for generated content, allowing experts to efficiently review, provide feedback, and rectify errors. The resulting golden discharge summaries are subsequently recorded for incremental fine-tuning of LLMs. Our project and demo video are in the GitHub repository https://github.com/ycycyc02/LCDS.
Open AccessLCDS: A Logic-Controlled Discharge Summary Generation System Supporting Source Attribution and Expert Review
Despite the remarkable performance of Large Language Models (LLMs) in automated discharge summary generation, they still suffer from hallucination issues, such as generating inaccurate content or fabricating information without valid sources. In addition, electronic medical records (EMRs) typically consist of long-form data, making it challenging for LLMs to attribute the generated content to the sources. To address these challenges, we propose LCDS, a Logic-Controlled Discharge Summary generation system. LCDS constructs a source mapping table by calculating textual similarity between EMRs and discharge summaries to constrain the scope of summarized content. Moreover, LCDS incorporates a comprehensive set of logical rules, enabling it to generate more reliable silver discharge summaries tailored to different clinical fields. Furthermore, LCDS supports source attribution for generated content, allowing experts to efficiently review, provide feedback, and rectify errors. The resulting golden discharge summaries are subsequently recorded for incremental fine-tuning of LLMs. Our project and demo video are in the GitHub repository https://github.com/ycycyc02/LCDS.
- Open Access
- 8 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 476-484
Towards Explainable Search Results in E-commerce
- 8 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 476-484
Open AccessTowards Explainable Search Results in E-commerce
- 15 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 29  (5) , 3642-3653
Decision Tree Extraction for Clinical Decision Support System With If-Else Pseudocode and PlanSelect Strategy
Decision trees, as a structured representation of medical knowledge, are critical resources for building clinical decision support systems. Their structured decision pathways can be used for retrieval to enhance clinical decision making. Currently, mainstream methods mainly utilize large language models and in-context learning for decision tree extraction. However, these methods often face challenges in understanding the structure of decision trees and accurately extracting the complete content of tree nodes, leading to noise in the extracted trees and ultimately impacting their effectiveness in clinical decision support system. To this end, in this paper, we propose a novel decision tree extraction framework, including two stages. In the first stage, we propose to use the If-Else pseudocode to represent the decision tree structure and design specific constraints on format and content to guide the LLM in generating outputs. In the second stage, we introduce a novel node-filling strategy called PlanSelect to match the extracted triplets with sub-sentences in the generated pseudocode, including four reasoning steps: observation, plan, action, and answer. To evaluate the effectiveness of our proposed method, we construct an English decision tree extraction dataset (EMDT) and conduct extensive experiments on the built and public datasets. Experiments on the Text2DT and EMDT datasets demonstrate that our method outperforms the current stateof- the-art approaches, achieving improvements of 1.37% and 1.54% on the $ER$ metric (which is lower is better), respectively. Furthermore, we use the medical decision trees extracted using our framework to improve the model's performance on clinical decision making tasks, i.e., CMBClin and MedQA. Our code and data are publicly available at https://github.com/nlper-hou/TSDTE.
- 15 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 29  (5) , 3642-3653
Decision Tree Extraction for Clinical Decision Support System With If-Else Pseudocode and PlanSelect Strategy
Decision trees, as a structured representation of medical knowledge, are critical resources for building clinical decision support systems. Their structured decision pathways can be used for retrieval to enhance clinical decision making. Currently, mainstream methods mainly utilize large language models and in-context learning for decision tree extraction. However, these methods often face challenges in understanding the structure of decision trees and accurately extracting the complete content of tree nodes, leading to noise in the extracted trees and ultimately impacting their effectiveness in clinical decision support system. To this end, in this paper, we propose a novel decision tree extraction framework, including two stages. In the first stage, we propose to use the If-Else pseudocode to represent the decision tree structure and design specific constraints on format and content to guide the LLM in generating outputs. In the second stage, we introduce a novel node-filling strategy called PlanSelect to match the extracted triplets with sub-sentences in the generated pseudocode, including four reasoning steps: observation, plan, action, and answer. To evaluate the effectiveness of our proposed method, we construct an English decision tree extraction dataset (EMDT) and conduct extensive experiments on the built and public datasets. Experiments on the Text2DT and EMDT datasets demonstrate that our method outperforms the current stateof- the-art approaches, achieving improvements of 1.37% and 1.54% on the $ER$ metric (which is lower is better), respectively. Furthermore, we use the medical decision trees extracted using our framework to improve the model's performance on clinical decision making tasks, i.e., CMBClin and MedQA. Our code and data are publicly available at https://github.com/nlper-hou/TSDTE.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 10517-10548
MinosEval: Distinguishing Factoid and Non-Factoid for Tailored Open-Ended QA Evaluation with LLMs
Yongqi Fan, Yating Wang, Guandong Wang, Zhai Jie, Jingping Liu, Qi Ye, Tong Ruan. Findings of the Association for Computational Linguistics: ACL 2025. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 10517-10548
Open AccessMinosEval: Distinguishing Factoid and Non-Factoid for Tailored Open-Ended QA Evaluation with LLMs
Yongqi Fan, Yating Wang, Guandong Wang, Zhai Jie, Jingping Liu, Qi Ye, Tong Ruan. Findings of the Association for Computational Linguistics: ACL 2025. 2025.
- Open Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 609-626
CMQCIC-Bench: A Chinese Benchmark for Evaluating Large Language Models in Medical Quality Control Indicator Calculation
Guangya Yu, Yanhao Li, Zongying Jiang, Yuxiong Jin, Li Dai, Yupian Lin, Ruihui Hou, Weiyan Zhang, Yongqi Fan, Qi Ye, Jingping Liu, Tong Ruan. Findings of the Association for Computational Linguistics: ACL 2025. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 609-626
Open AccessCMQCIC-Bench: A Chinese Benchmark for Evaluating Large Language Models in Medical Quality Control Indicator Calculation
Guangya Yu, Yanhao Li, Zongying Jiang, Yuxiong Jin, Li Dai, Yupian Lin, Ruihui Hou, Weiyan Zhang, Yongqi Fan, Qi Ye, Jingping Liu, Tong Ruan. Findings of the Association for Computational Linguistics: ACL 2025. 2025.