Dialogue Summarization with Mixture of Experts based on Large Language Models
Yuanhe Tian, Fei Xia, Yan Song
Abstract
DIALOGUE S1: Hi, Mr. Smith. I'm Doctor Hawkins. Why are you here today? S2: I found it would be a good idea to get a check-up. S1: Yes, well, you haven't had one for 5 years. You should have one every year. S2: I know. I figure as long as there is nothing wrong, why go see the doctor? S1: Well, the best way to avoid serious illnesses is to find out about them early. So try to come at least once a year for your own good. S2: Ok. S1: Let me see here. Your eyes and ears look fine. Take a deep breath, please. Do you smoke, Mr. Smith? S2: Yes. S1: Smoking is the leading cause of lung cancer and heart disease, you know. You really should quit. S2: I've tried hundreds of times, but I just can't seem to kick the habit. S1: Well, we have classes and some medications that might help. I'll give you more information before you leave. S2: Ok, thanks doctor.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 03c11ebd-010e-4fc0-b512-e26e3a5173bfCited by top-tier papers5
- On the Risk of Evidence Pollution for Malicious Social Text Detection in the Era of LLMsHerun Wan, Minnan Luo, Zhixiong Su, Guang Dai et al.ACL 2025 · 5 citations
- RCMoE: A Communication-Efficient Random Compression Framework for Resource-Constrained Mixture-of-Experts TrainingDonglei Wu, Xiao Cai, Jinglei Tan, Jinda Jia et al.AAAI 2026
- Too Helpful, Too Harmless, Too Honest or Just Right?Gautam Siddharth Kashyap, Mark Dras, Usman NaseemEMNLP 2025
- ArgCMV: An Argument Summarization Benchmark for the LLM-eraOmkar Gurjar, Agam Goyal, Eshwar ChandrasekharanEMNLP 2025
- Task-aware Contrastive Mixture of Experts for Quadruple Extraction in Conversations with Code-like Replies and Non-opinion DetectionChenyuan He, Yuxiang Jia, Fei Gao, Senbin Zhu et al.EMNLP 2025
Builds on20
- Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma et al.NeurIPS 2022 · 22,562 citations
- BERTScore: Evaluating Text Generation with BERTTianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q. Weinberger et al.ICLR 2020 · 8,443 citations
- BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and ComprehensionMike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad et al.ACL 2020 · 1,224 citations
- GLaM: Efficient Scaling of Language Models with Mixture-of-ExpertsNan Du, Yanping Huang, Andrew M. Dai, Simon Tong et al.ICML 2022 · 1,173 citations
- Multimodal Contrastive Learning with LIMoE: the Language-Image Mixture of ExpertsBasil Mustafa, Carlos Riquelme, Joan Puigcerver, Rodolphe Jenatton et al.NeurIPS 2022 · 359 citations
Related papers
- Evaluating the Gradual Delivery of Knowledge-focused and Mindset-focused Messages for Facilitating the Acceptance of COPDSteven Y. Zeng, Robert C. Wu, Khai N. Truong, Fanny ChevalierUbiComp 2021 · 8 citations
- Dialogue Based Disease Screening Through Domain Customized Reinforcement LearningZhuo Liu, Yanxuan Li, Xingzhi Sun, Fei Wang et al.KDD 2021 · 8 citations
- Assertiveness-based Agent Communication for a Personalized Medicine on Medical Imaging DiagnosisFrancisco Maria Calisto, João Gabriel de Matos Fernandes, Margarida Morais, Carlos Santiago et al.CHI 2023 · 94 citations
- Follow-up Question Generation For Enhanced Patient-Provider ConversationsJoseph Gatto, Parker Seegmiller, Timothy E. Burdick, Inas S. Khayal et al.ACL 2025
- Towards Trustworthy Automatic Diagnosis Systems by Emulating Doctors' Reasoning with Deep Reinforcement LearningArsène Fansi Tchango, Rishab Goel, Julien Martel, Zhi Wen et al.NeurIPS 2022 · 14 citations
