Emotion-Aware Dialogue Generation

Follow this topic Ask about this topic

Momentum

5 papers in the last four weeks, up 67% on the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 38

All topics

Thinking in Depth, Speaking Directly: Recurrent Latent Reasoning for Paralinguistically Grounded Spoken Dialogue
Sep 29, 2026Shengbo Cai, Yuxiang Wang, Jingran Xie +5Audio Reasoning Speech Language Models
Tsinghua University · Tencent Hunyuan · The Chinese University of Hong Kong, Shenzhen
Evolving Support Priorities in Empathetic Reinforcement Learning
Sep 28, 2026Pengyu Huang, Zhiyuan Han, Wenwen Tong +6Reward Modeling RL for Language Models
University of Science and Technology of China, Hefei, China · SenseTime Research, Shanghai, China · Institute of Artificial Intelligence, Hefei Comprehensive National Science Center
RoleBreak: Benchmarking Long-Horizon Role-Playing Robustness in Spoken Dialogue
Sep 15, 2026Yuqi Wang, Fengyuan Liu, Haochen Luo +2Large Language Model-Based Role-Play Simulation Speech Generation Evaluation
The University of Hong Kong · Kami AI
ER-EDF: A Psychology-Grounded Emotion Regulation Framework for Speech Empathetic Dialogue Generation in Large Audio-Language Models
Sep 14, 2026Hongyu Jin, Wenda Zhang, Runqiu Fei +3Spoken Dialogue Systems Audio-Language Models
EmoMed: An Emotionally-Aware Agent for Multimodal Medical Support with Real-Time Information Retrieval
Sep 7, 2026Ivan Nasonov, Nikita Glazkov, Ivan Makovetskiy +4Conversational Agents Multimodal Agents
ISP RAS Research Center for Trusted Artificial Intelligence, 109004 Moscow, Russia · AXXX, 119049 Moscow, Russia · National University of Science and Technology (NUST) MISIS, 119049 Moscow, Russia +2
PragAlign: Feedback-Guided Pragmatic Alignment for Controlled Synthetic Dialogue Generation
Sep 2, 2026Smitha Muthya Sudheendra, Jaideep SrivastavaText Generation Controllable Text Generation
University of Minnesota, Twin Cities
EmoStance: Response-Side Affective-Orientation Control for Empathetic Response Generation via Emoji Weak Supervision
Sep 2, 2026Ziyuan Jin, Yuxuan Ge, Zheng TianEmotion-Aware Dialogue Generation Controllable Text Generation
ShanghaiTech University, Shanghai, China
Dual-Loop Self-Evolution via Verifiable Emotion Feedback for Multi-Turn Empathetic Dialogue
Aug 11, 2026Yi Wei, Shuo Jiang, Huaixia Dou +5Reinforcement Learning with Verifiable Rewards Curriculum Learning
Qwen DianJin Team, Alibaba Cloud Computing · Beihang University · School of Computer Science and Technology, Soochow University
EmpaAva: An Open-source Agentic 3D-Avatar Empathetic Live Chatbot
Aug 5, 2026Jie Yang, Wenhao Xu, Shuhui Lin +1Conversational Agents Multimodal Agents
National University of Singapore · Tsinghua University · University of Oxford
Towards More Expressive Spoken LLMs: Fine-Grained Intent Benchmarking and Acoustic-Lexical Decoupled Policy Optimization
Aug 4, 2026Xiang Lin, Tian-Hao Zhang, Chunfeng Wang +3RL for Language Models Spoken Dialogue Systems
Li Auto Inc., Beijing, China · Tsinghua University, Beijing, China
JoyAI-Talker: Full-Duplex Speech Interactive Large Model Built for Empathetic Voice Agents
Aug 2, 2026Yinhao Bai, Jinming Chen, Yafeng Chen +26Speech Foundation Models Controllable Speech Generation
EmoTrace: An Emotion Trajectory-Centered Framework for Psychological Support Dialogue Generation
Jul 26, 2026Kaitong Weng, Lixin Liu, Zihao Liu +2Mental Health Counseling Emotional Support Conversation
Shenzhen International Graduate School, Tsinghua University
Dynamic Commonsense Coordination for Empathetic Response Generation
Jul 24, 2026Zhengyu QiKnowledge Augmentation for Language Models Emotion-Aware Dialogue Generation
Leiden Institute of Advanced Computer Science (LIACS) Leiden University, The Netherlands
ZifaMem: Structured Memory for Persona, Preference, and Emotional Continuity in AI Companions
Jul 20, 2026Jingzhe Fang, Guozhi Xu, Yunfan Cui +2LLM Agent Memory Persistent Memory for Language Models
ZifaCorp · University of Science and Technology of China · Fudan University
Back to the museum: Investigation of the acceptance of Android Andrea with and without emotion simulation in a museum
Jul 17, 2026Marcel Heisler, Christian Becker-AsanoRobotics Human-Robot Interaction
Hochschule der Medien · Stuttgart, Germany
Vision-Language Assistant for Emotional Reactions to Risky Driving
Jul 17, 2026Harine Choi, Eun Hak Lee, Zhengzhong TuConversational Agents Emotion-Aware Dialogue Generation
Department of Computer Science and Engineering, Texas A&M University, 77840, College Station, Texas, United States · School of Railway Operation Systems, Kyungil University, Gyeongsan-si, Gyeongsangbuk-do, Republic of Korea
From Triggers to Emotions: A CPM-Grounded Appraisal Multi-Agent for Dynamic Emotional Evolution in Persona-Based Dialogue
Jul 8, 2026Jingyao Cai, Shuaijun Liu, Abdul Rehman +6Multi-Agent LLM Systems Personality Modeling in Language Models
National Centre for Computer Animation, Bournemouth University, Bournemouth, United Kingdom · Information Hub, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China · Key Laboratory of Child Cognition & Behavior Development of Hainan Province, Qiongtai Normal University, Haikou, China +2
SPLIT: Cross-Lingual Empathy and Cultural Grounding in English and Ukrainian LLM Responses
Jul 2, 2026Anna ChornaMultilingual Language Model Evaluation LLM-as-a-Judge
PRIDE: Privileged Information-enhanced Distillation for Empathetic Dialogue Generation
Jun 22, 2026Jiaqiang Wu, Zhouan Zhu, Shangfei WangLanguage Model Distillation Learning Using Privileged Information
Anhui Robot Technology Standard Innovation Base, School of Computer Science and Technology, University of Science and Technology of China, Hefei, Anhui 230027, PR China
EIBench: A Simulator-Based Benchmark and Turn-Credit RL for Emotion Management
Jun 14, 2026Rongzhi Zhu, Xiang Huang, Yuchuan Wu +8RL for Language Models LLM Evaluation
State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing 210023, China · Qwen-Character Team , Alibaba Group
PRISM: Prosody-Integrated Multi-Agent Reasoning Framework for Empathetic Spoken Dialogue
Jun 11, 2026Wen Zhang, Xiaocui Yang, Zhuoyue Gao +3Multi-Agent LLM Systems Spoken Dialogue Systems
School of Computer Science and Engineering, Northeastern University, Shenyang 110819, China
I Understand How You Feel: Enhancing Deeper Emotional Support Through Multilingual Emotional Validation in Dialogue System
Jun 10, 2026Zi Haur Pang, Yahui Fu, Koji Inoue +1Emotional Support Conversation Spoken Dialogue Systems
Graduate School of Informatics, Kyoto University, Japan
Beyond Semantic Dominance: Cognitive Affective Reasoning and Empathetic Response Alignment in Audio Language Models
Jun 5, 2026Zhixian Zhao, Shuiyuan Wang, Wenjie Tian +3CoT Reasoning Audio Understanding
Resonant Minds: Closed-Loop Social Avatars with Theory of Mind
Jun 4, 2026Jianxu Shangguan, Jing Xu, Hang Ye +4Audio-Video Generation Theory of Mind
University of Washington · 2Peking University · 3Carnegie Mellon University +1
Sympatheia: Emotionally Adaptive Voice Assistant with Continuous Affect Conditioning
May 30, 2026Sukru Samet Dindar, Riki Shimizu, Xilin Jiang +1Spoken Dialogue Systems Controllable Speech Generation
Department of Electrical Engineering Columbia University New York, NY 10025
From Empathy to Personalized Empathy: Adapting Empathetic Strategies to Individual Users
May 30, 2026Wuqiang Zheng, Chengbing Wang, Yilin Yang +6Reward Modeling LLM Personalization
University of Science and Technology of China · 2Huawei Technologies · 3China Academy of Cyber
EmoDistill: Offline Emotion Skill Distillation for Language Model Agents in Adversarial Negotiation
May 26, 2026Yunbo Long, Haolang Zhao, Lukas Beckenbauer +2Multi-Agent Negotiation Automated Negotiation
University of Cambridge · Technical University of Munich · Exiger LLC +1
AttuneBench: A Conversation-Based Benchmark for LLM Emotional Intelligence
May 20, 2026Kate M. Lubrano, Faisal Sayed, Ankita Rathod +4LLM Evaluation Emotion Recognition in Conversations
1Pareto, California, US · 2Thoughtful, California, US · University of Pennsylvania, Pennsylvania, US
Toward Natural and Companionable Virtual Agents via Cross-Temporal Emotional Modeling
May 15, 2026Feier Qin, Xiao Li, Yi Zheng +5Long-Horizon LLM Agents Memory-Augmented Agents
Communication University of China BeiJing, China · Microsoft Research Asia BeiJing, China · Institute of Artificial Intelligence, China Telecom BeiJing, China
Emotion-Attended Stateful Memory (EASM):The Architecture for Hyper-Personalization at Scale
May 14, 2026Vineet Kotecha, Vansh GuptaMemory-Augmented Language Models Personalized Language Models
divAIne Research

Sep 29, 2026, cs.CLJ/K move · Enter open · S save

Thinking in Depth, Speaking Directly: Recurrent Latent Reasoning for Paralinguistically Grounded Spoken Dialogue

Shengbo Cai, Yuxiang Wang, Jingran Xie, Zhisheng Zhang+4

Tsinghua University · Tencent Hunyuan · The Chinese University of Hong Kong, Shenzhen

Audio Reasoning Speech Language Models Emotion-Aware Dialogue Generation

Open paper AskPDF arXiv

Empathetic spoken dialogue requires models to use both what is said and how it is said to decide how to respond. Explicit CoT can improve paralinguistic perception and make acoustic cues more explicit in replies, yet does not ensure their effective use in response planning. We call this mismatch the perception-reasoning gap. In addition, CoT may not fully capture acoustic cues in words, and generating it adds inference latency. To address these limitations, we introduce LoopSLM, which builds on looped Transformers for latent reasoning, reusing a decoder block to refine hidden states with acoustic grounding at every pass. Its two-stage training further narrows the perception-reasoning gap by separating learning to reason from learning to respond, enabling direct inference without CoT. On EchoMind, LoopSLM improves paralinguistic understanding, reasoning, and reply quality over Qwen2.5-Omni-7B. Against the CoT-SFT baseline, LoopSLM gains over 20 points in reasoning accuracy while generating 64.5% fewer tokens at half the latency. It also outperforms Qwen3-Omni-Thinking on most empathetic reply metrics with 34x lower latency. Despite training only on dialogue data, LoopSLM improves accuracy on general audio benchmarks.

Momentum

Related topics

Latest papers 38