Facilitating Multi-turn Emotional Support Conversation with Positive Emotion Elicitation: A Reinforcement Learning Approach
Open accessAbstract
Emotional support conversation (ESC) aims to provide emotional support (ES) to improve one's mental state.Existing works stay at fitting grounded responses and responding strategies (e.g., question), which ignore the effect on ES and lack explicit goals to guide emotional positive transition.To this end, we introduce a new paradigm to formalize multi-turn ESC as a process of positive emotion elicitation.Addressing this task requires finely adjusting the elicitation intensity in ES as the conversation progresses while maintaining conversational goals like coherence.In this paper, we propose SUPPORTER, a mixture-of-expert-based reinforcement learning model, and well design ES and dialogue coherence rewards to guide policy's learning for responding.Experiments verify the superiority of SUPPORTER in achieving positive emotion elicitation during responding while maintaining conversational goals including coherence.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Existing agents-based LLMs are still incompetent in accomplishing social goals, e.g., rethinking the past conversation and establishing long-term connections with humans.
“Despite their great success, existing agentsbased LLMs are still incompetent in accomplishing social goals (Zhou et al., 2023), e.g., rethinking the past conversation and establishing long-term connections with humans.”
From Recursively summarizing enables long-term dialogue memory in large language models (2025) · cites this paper as Zhou et al., 2023
The Introduction says existing emotional-support conversation systems lack explicit goals for improving a user's mental state across multiple turns. That supports a narrower claim about a social goal in emotional-support dialogue, but not the broader claim about agent-based LLMs or the examples of rethinking past conversations and establishing long-term human connections. The indexed passages provide section labels but no page numbers. (LLM, conf=0.84)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · see citing works
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 48,293 · see citing works
Reinforcement Learning: An Introduction
Sutton, R. S., & Barto, A. G. (1998) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.1998.712192 · Cited by 27,225 · see citing works
Neural Machine Translation by Jointly Learning to Align and Translate
Bahdanau, D., Cho, K., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1409.0473 · Cited by 16,213 · see citing works
Lewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A., Levy, O., Stoyanov, V., & Zettlemoyer, L. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.703 · Cited by 8,821 · see citing works
Word association norms, mutual information, and lexicography
Church, K. W., & Hanks, P. (1989) · Proceedings of the 27th annual meeting on Association for Computational Linguistics - · doi:10.3115/981623.981633 · Cited by 1,094 · see citing works
SOCIAL NETWORKS AND SOCIAL SUPPORT
(2016) · The Gerontologist · doi:10.1093/geront/gnw162.1463 · Cited by 1,004 · see citing works
COMET: Commonsense Transformers for Automatic Knowledge Graph Construction
Bosselut, A., Rashkin, H., Sap, M., Malaviya, C., Celikyilmaz, A., & Choi, Y. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1470 · Cited by 904 · see citing works
Towards Empathetic Open-domain Conversation Models: A New Benchmark and Dataset
Rashkin, H., Smith, E. M., Li, M., & Boureau, Y.-L. (2019) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/p19-1534 · Cited by 883 · see citing works
Recipes for Building an Open-Domain Chatbot
Roller, S., Dinan, E., Goyal, N., Ju, D., Williamson, M., Liu, Y., Xu, J., Ott, M., Smith, E. M., Boureau, Y.-L., et al. (2021) · Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume · doi:10.18653/v1/2021.eacl-main.24 · Cited by 784 · see citing works
Obtaining Reliable Human Ratings of Valence, Arousal, and Dominance for 20,000 English Words
Mohammad, S. M. (2018) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/p18-1017 · Cited by 616 · see citing works
Challenges in building intelligent open-domain dialog systems
Huang, M., Zhu, X., & Gao, J. (2020) · ACM Transactions on Information Systems · doi:10.1145/3383123 · Cited by 288 · see citing works
Self-citationTowards Emotional Support Dialog Systems
Liu, S., Zheng, C., DeMasi, O., Sabour, S., Yu, L., Yu, Z., Jiang, Y., & Huang, M. (2021) · Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2021.acl-long.269 · Cited by 286 · see citing works
Self-citationMoEL: Mixture of Empathetic Listeners
Lin, Z., Madotto, A., Shin, J., Xu, P., & Fung, P. (2019) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d19-1012 · Cited by 236 · see citing works
MIME: MIMicking Emotions for Empathetic Response Generation
Majumder, N., Hong, P., Peng, S., Lu, J., Ghosal, D., Gelbukh, A. F., Mihalcea, R. F., & Poria, S. (2020) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.721 · Cited by 216 · see citing works
An Introduction to Cognitive Behaviour Therapy – Skills and Applications
Russell, P. A. (2008) · Nursing Standard · doi:10.7748/ns.22.20.30.s37 · Cited by 181 · see citing works
CEM: Commonsense-Aware Empathetic Response Generation
Sabour, S., Zheng, C., & Huang, M. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i10.21373 · Cited by 158 · see citing works
Self-citationMishara, B. L., Chagnon, F., Daigle, M. S., Balan, B., Raymond, S., Marcoux, I., Bardon, C., Campbell, J. K., & Berman, A. L. (2007) · Suicide and Life-Threatening Behavior · doi:10.1521/suli.2007.37.3.308 · Cited by 142 · see citing works
EmpDG: Multi-resolution Interactive Empathetic Dialogue Generation
Li, Q., Chen, H., Ren, Z., Ren, P., Tu, Z., & Chen, Z. (2020) · International Conference on Computational Linguistics · doi:10.18653/v1/2020.coling-main.394 · Cited by 142 · see citing works
Self-citationKnowledge Bridging for Empathetic Dialogue Generation
Li, Q., Li, P., Ren, Z., Ren, P., & Chen, Z. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i10.21347 · Cited by 120 · see citing works
Self-citationTarget-Guided Open-Domain Conversation
Tang, J., Zhao, T., Xiong, C., Liang, X., Xing, E. P., & Hu, Z. (2019) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/p19-1565 · Cited by 117 · see citing works
Peng, W., Hu, Y. H., Xing, L., Xie, Y., Sun, Y., & Li, Y. (2022) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2022/600 · Cited by 87 · see citing works
MISC: A Mixed Strategy-Aware Model integrating COMET for Emotional Support Conversation
Tu, Q., Li, Y., Cui, J., Wang, B., Wen, J.-R., & Yan, R. (2022) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2022.acl-long.25 · Cited by 86 · see citing works
Self-citationLubis, N., Sakti, S., Yoshino, K., & Nakamura, S. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11955 · Cited by 79 · see citing works
Burleson, B. R. (2003) · Routledge eBooks · doi:10.4324/9781410607133-22 · Cited by 74 · see citing works
CoMAE: A Multi-factor Hierarchical Framework for Empathetic Response Generation
Zheng, C., Liu, Y., Chen, W., Leng, Y., & Huang, M. (2021) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2021.findings-acl.72 · Cited by 70 · see citing works
Self-citationPredicting and Eliciting Addressee's Emotion in Online Dialogue
Hasegawa, T., Kaji, N., Yoshinaga, N., & Toyoda, M. (2013) · Cited by 60 · see citing works
From what isn’t Empathy to Empathic Learning Process
Keskin, S. C. (2014) · Procedia - Social and Behavioral Sciences · doi:10.1016/j.sbspro.2014.01.1052 · Cited by 52 · see citing works
Improving Multi-turn Emotional Support Dialogue Generation with Lookahead Strategy Planning
Cheng, Y., Liu, W., Li, W., Wang, J., Zhao, R., Liu, B., Liang, X., & Zheng, Y. (2022) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2022.emnlp-main.195 · Cited by 50 · see citing works
Positive Emotion Elicitation in Chat-Based Dialogue Systems
Lubis, N., Sakti, S., Yoshino, K., & Nakamura, S. (2019) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2019.2900910 · Cited by 44 · see citing works
CASE: Aligning Coarse-to-Fine Cognition and Affection for Empathetic Response Generation
Zhou, J., Zheng, C., Wang, B., Zhang, Z., & Huang, M. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-long.457 · Cited by 38 · see citing works
Self-citationRains, S. A., Pavlich, C. A., Lutovsky, B. R., Tsetsi, E., & Ashtaputre, A. (2019) · Journal of Social and Personal Relationships · doi:10.1177/0265407519876359 · Cited by 26 · see citing works
Conversational system for information navigation based on POMDP with user focus tracking
Yoshino, K., & Kawahara, T. (2015) · Computer Speech & Language · doi:10.1016/j.csl.2015.01.003 · Cited by 26 · see citing works
Emotional support and its relationship to Emotional intelligence
Atoum, A. Y., & Al-Shoboul, R. A. (2018) · Advances in Social Sciences Research Journal · doi:10.14738/assrj.51.4095 · Cited by 22 · see citing works
Shibata, T., Egashira, Y., & Kurohashi, S. (2016) · Signals and communication technology · doi:10.1007/978-3-319-21834-2_6 · Cited by 17 · see citing works
Emotion Eliciting Machine: Emotion Eliciting Conversation Generation based on Dual GeneratorPreprint
Jiang, H., Zhu, Y., Zhang, X., Dou, Z., Du, P., Pi, T., & Jia, Y. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.08251 · Cited by 2 · see citing works
Towards Multi-Turn Empathetic Dialogs with Positive Emotion ElicitationPreprint
Wang, S., Xu, X., Wu, W., Niu, Z.-Y., Wu, H., & Wang, H. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2204.10509 · Cited by 2 · see citing works
Flagged first, then by citations
Research works printed but not linked: 2
- Nurul Lubis, Sakriani Sakti, Koichiro Yoshino, and Satoshi Nakamura. 2019a. Dialogue model and re- sponse generation for emotion improvement elici- tation. In Proc. 33rd Conf. Neural Inf. Process. Syst.(NIPS), pages 1-11.
- Richard S Sutton and Andrew G Barto. 2018. Reinforce- ment learning: An introduction. MIT press.
Cited by
Sorted by citations
Recursively summarizing enables long-term dialogue memory in large language models
Wang, Q., Fu, Y., Cao, Y., Wang, S., Tian, Z., & Ding, L. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.130193 · Cited by 55 · see citing works
Proactive Conversational AI: A Comprehensive Survey of Advancements and Opportunities
Deng, Y., Liao, L., Lei, W., Yang, G. H., Lam, W. P., & Chua, T. (2025) · ACM Transactions on Information Systems · doi:10.1145/3715097 · Cited by 45 · see citing works
Zheng, W., Yu, J., & Xia, R. (2024) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3664647.3681638 · Cited by 12 · see citing works
Dynamic Demonstration Retrieval and Cognitive Understanding for Emotional Support Conversation
Xu, Z., Chen, D., Kuang, J., Yi, Z., Li, Y., & Shen, Y. (2024) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3626772.3657695 · Cited by 10 · see citing works
Cooper: Coordinating Specialized Agents towards a Complex Dialogue Goal
Cheng, Y., Liu, W., Wang, J., Leong, C. T., Ouyang, Y., Li, W., Wu, X., & Zheng, Y. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i16.29739 · Cited by 9 · see citing works
Empathetic Dialogue Generation with LLMs for Emotional Support
Wang, S., Fang, R., Li, M., He, Z., & Song, S. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-3352-7_45 · Cited by 7 · see citing works
Breaking the Silence: Whisper-Driven Emotion Recognition in AI Mental Support Models
Qu, X., Sun, Z., Feng, S., Chen, C., & Tian, T. (2024) · IEEE Conference on Artificial Intelligence (CAI) · doi:10.1109/cai59869.2024.00063 · Cited by 5 · see citing works
Tu, G., Wang, B., Cambria, E., Li, W., & Xu, R. (2025) · International World Wide Web Conference (WWW) · doi:10.1145/3701716.3715200 · Cited by 4 · see citing works
Self-citationPersona Extraction Through Semantic Similarity for Emotional Support Conversation Generation
Han, S., Park, S. J., Kim, C. W., & Ro, Y. M. (2024) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp48485.2024.10445957 · Cited by 3 · see citing works
Li, J., Peng, B., Hsu, Y.-Y., & Huang, C. (2024) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2024.emnlp-main.118 · Cited by 3 · see citing works
Enhancing Emotional Support Conversation with Cognitive Chain-of-Thought Reasoning
Cao, Y., Chen, Z., Bi, G., Feng, Y., Chen, M., Wan, F., Huang, M., & Yu, H. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-9431-7_14 · Cited by 2 · see citing works
Self-citationEmstremo: Adapting Emotional Support Response with Enhanced Emotion-Strategy Integrated Selection
Li, J., Peng, B., & Hsu, Y.-Y. (2024) · Language Resources and Evaluation Conference (LREC) · doi:10.63317/4ywd639z4qec · Cited by 2 · see citing works
Persona-Identified Chatbot through Small-Scale Modeling and Data Transformation
Keum, B., Sun, J., Lee, W., Park, S., & Kim, H. (2024) · Electronics · doi:10.3390/electronics13081409 · Cited by 2 · see citing works
Producing Considerate Responses: Progressive Staged Training for Emotional Support Conversation
Lv, G., Li, J., Wang, X., Zhan, X., & Zeng, Z. (2024) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2024.3477531 · Cited by 2 · see citing works
Applying Emotion-Cause Entailment for Help-Seeker Guidance in Emotional Support Conversations
Chang, J., & Wu, C. (2025) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2025.3605971 · Cited by 1 · see citing works
Huang, Y., Li, L., Dong, W., Dong, Y., Huang, Y., & Liu, H. (2024) · doi:10.2196/preprints.65435
InsideOut: Unifying Emotional LLMs to Foster Empathy
Mozikov, M., Severin, N., Glushanina, M., Baklashkin, M., Savchenko, A., & Makarov, I. (2024) · Frontiers in artificial intelligence and applications · doi:10.3233/faia241039
Mind2: Mind-to-Mind Emotional Support System with Bidirectional Cognitive Discourse Analysis
Hong, S. Y., Oyshi, U., Mai, Q., Nkhata, G., & Gauch, S. (2024) · IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT) · doi:10.1109/wi-iat62293.2024.00023
Optimizing LLMs for Personalized Emotional Support with Future Cues and Response Diversity
Song, J., Zan, H., Liu, H., Li, Y., Kong, L., Cheng, X., Zhang, K., & Peng, M. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-3352-7_44
Modeling Long-Term Emotional Support Through Causal World Modeling With Imitation Learning
Li, M., Wang, F., Li, K., Wei, Y., Nie, Y., Hao, Y., Yang, X., & Wang, M. (2026) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2026.3653579
Adaptive Persona Context Modulation for Personalized Emotional Support Conversation
Wang, H., Yang, X., Wang, D., Feng, S., & Zhang, Y. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-7081-2_24
Liu, C., Bao, J., Chen, T., Huang, B., Gan, Y., Huang, F., & Tao, X. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6294407
Ma, M., Guo, B., Chen, M., Liu, J., Ding, Y., Liu, Y., & Wang, H. (2026) · International World Wide Web Conference (WWW) · doi:10.1145/3774904.3792335
Hwang, S., Shim, M., Gong, Y., Kim, D., & Lee, K.-H. (2026) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2026.3703303
Calambur, V., Young, J., Razi, A., & Huh, J. (2026) · ACM Transactions on Computing for Healthcare · doi:10.1145/3817048
Causal-ESC: Reliable Policy Learning for Emotional Support Conversation via Causal Inference
Wang, X., Zhenyu, W., Zheng, G., & Zhang, R. (2026) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2026.acl-long.886
ACE-GoT: Affective and Contextual Expansion via Graph-of-Thought for Emotional Support Conversations
Xue, C.-S., Chen, H.-Y., Wu, C., & Chen, C. (2026) · IEEE Access · doi:10.1109/access.2026.3720767
EEG-ESC: An Affective Brain-Computer Interface for Adaptive Emotional Support Dialogue
Chen, C., Shen, C., Wu, D., & Shi, X. (2026) · IEEE China Conference on System Simulation Technology and its Applications (CCSSTA) · doi:10.1109/ccssta69471.2026.11635470
A Comprehensive Dataset and Benchmark for Empathetic Responses in Online Communities
Qi, S., Lyu, J., Liao, M., Xiang, R., & Li, J. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-5696-9_16
AutoPal: Autonomous Adaptation to Users for Personal AI Companionship
Cheng, Y., Liu, W., Xu, K., Hou, W., Ouyang, Y., Leong, C. T., Li, W., Wu, X., & Zheng, Y. (2024) · arXiv · doi:10.48550/arxiv.2406.13960 · Cited by 2 · see citing works
- Authors
- Zhou, J., Chen, Z., Wang, B., & Huang, M.
- Affiliations
- Tianjin University (CN)
- State Key Laboratory of Intelligent Technology and Systems (CN)
- Venue
- Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Published
- 2023
- Pages
- 1714-1729
- ISSN
- 0736-587X (ISSN-L)
- OpenAlex
- W4385569827
- Cited by
- 25
- References
- 37
- Citations by year
- 2026: 8 · 2025: 6 · 2024: 11
- FWCI
- 4.43
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Proceedings of the conference - Association for Computational Linguistics. Meeting (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion, cc-by)
- arXiv (Cornell University) (cc-by)
- Funders
- National Science Foundation
- National Natural Science Foundation of China (62276187, 62272340, 61876128)
- Tsinghua University
- National Science Fund for Distinguished Young Scholars (62125604)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Speech and dialogue systems
- Social Sciences › Psychology › Experimental and Cognitive Psychology › Emotion and Mood Recognition
- Physical Sciences › Computer Science › Artificial Intelligence › Intelligent Tutoring Systems and Adaptive Learning
- Keywords
- emotional support conversation, multi-turn dialogue, mixture of experts, dialogue coherence, chatbots
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
