Keyan Jin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Keyan Jin has a total of 33 co-authors. Here are the top co-authors by number of shared publications:
- Tao Fang
Guangdong Institute of Intelligence Science and Technology, Zhuhai, Guangdong, China
5 shared publications - Derek Fai Wong
University of Macau
3 shared publications - Yapeng Wang
Macao Polytechnic University
3 shared publications - Francisco Javier Blanco-Encomienda
Universidad de Granada
2 shared publications - Hugo Gonçalo Oliveira
University of Coimbra
2 shared publications - Jiechao Gao
Stanford University, Stanford, USA
2 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 14868-14877
Agri-Cure: Curriculum Remedy Unlocks GRPO for Imbalanced Agricultural Disease Reasoning
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 14868-14877
Open AccessAgri-Cure: Curriculum Remedy Unlocks GRPO for Imbalanced Agricultural Disease Reasoning
- Open Access
- 11 August 2026
- Published by Elsevier in Journal of Industrial Information Integration
- Vol. 53
A scalable framework for building and validating knowledge-driven synthetic consumer agents with large language models
- 11 August 2026
- Published by Elsevier in Journal of Industrial Information Integration
- Vol. 53
Open AccessA scalable framework for building and validating knowledge-driven synthetic consumer agents with large language models
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1709-1718
Distribution-aware Re-representations for Multi-Scenario Recommendations
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1709-1718
Open AccessDistribution-aware Re-representations for Multi-Scenario Recommendations
- Open Access
- 22 May 2026
- Published by Elsevier in Information Processing & Management
- Vol. 63 (8)
Densifying Knowledge Hypergraphs with LLM-based review distillation for conversational consumer decision support
- 22 May 2026
- Published by Elsevier in Information Processing & Management
- Vol. 63 (8)
Open AccessDensifying Knowledge Hypergraphs with LLM-based review distillation for conversational consumer decision support
- 20 November 2025
- Published by Elsevier in Applied Soft Computing
- Vol. 187
Role-aware adapters for dialogue summarization in Seq2Seq models
- 20 November 2025
- Published by Elsevier in Applied Soft Computing
- Vol. 187
Role-aware adapters for dialogue summarization in Seq2Seq models
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 6075-6083
Prototype-Guided Representation Projection for Multi-Domain Multi-Task Recommendation
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 6075-6083
Open AccessPrototype-Guided Representation Projection for Multi-Domain Multi-Task Recommendation
- 25 September 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 299
Reasoning or not? A comprehensive evaluation of reasoning LLMs for dialogue summarization
- 25 September 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 299
Reasoning or not? A comprehensive evaluation of reasoning LLMs for dialogue summarization
- 10 April 2025
- Published by Wiley in Expert Systems
- Vol. 42 (5)
HiSum: Hierarchical Topic‐Driven Approach for Role‐Oriented Dialogue Summarisation
As the volume of information on online communication platforms continues to grow, the task of dialogue summarisation becomes increasingly critical for understanding and extracting key information from diverse conversations. Traditional approaches often struggle to cope with the dynamic nature of dialogues, such as managing perspectives from multiple speakers and seamlessly transitioning between different topics. We propose a novel hierarchical topic‐driven approach to generate role‐oriented dialogue summarisation (HiSum) to address these challenges. First, we utilise VarGMM clustering technology for in‐depth topic segmentation, which enables the model to capture the key topics in a dialogue. Second, we employ a LayerAttn hierarchical attention mechanism to dynamically adjust the focus of dialogue content based on participants' importance and the topics' relevance. Experimental results on three public dialogue summarisation data sets (CSDS, MC and SAMSUM) demonstrate that our method significantly outperforms most existing strong baseline methods across various evaluation metrics and surpasses the current state‐of‐the‐art methods in certain metrics. Detailed analysis demonstrates that HiSum can perform more precise topic segmentation and effectively identify critical information. Our code is publicly available at: https://github.com/kjin0119/HiSum.
- 10 April 2025
- Published by Wiley in Expert Systems
- Vol. 42 (5)
HiSum: Hierarchical Topic‐Driven Approach for Role‐Oriented Dialogue Summarisation
As the volume of information on online communication platforms continues to grow, the task of dialogue summarisation becomes increasingly critical for understanding and extracting key information from diverse conversations. Traditional approaches often struggle to cope with the dynamic nature of dialogues, such as managing perspectives from multiple speakers and seamlessly transitioning between different topics. We propose a novel hierarchical topic‐driven approach to generate role‐oriented dialogue summarisation (HiSum) to address these challenges. First, we utilise VarGMM clustering technology for in‐depth topic segmentation, which enables the model to capture the key topics in a dialogue. Second, we employ a LayerAttn hierarchical attention mechanism to dynamically adjust the focus of dialogue content based on participants' importance and the topics' relevance. Experimental results on three public dialogue summarisation data sets (CSDS, MC and SAMSUM) demonstrate that our method significantly outperforms most existing strong baseline methods across various evaluation metrics and surpasses the current state‐of‐the‐art methods in certain metrics. Detailed analysis demonstrates that HiSum can perform more precise topic segmentation and effectively identify critical information. Our code is publicly available at: https://github.com/kjin0119/HiSum.
- 4 April 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 279
LLMCL-GEC: Advancing grammatical error correction with LLM-driven curriculum learning
- 4 April 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 279
LLMCL-GEC: Advancing grammatical error correction with LLM-driven curriculum learning