Elamur Research⌕
☰
home / papers / 2026 / Topic-Initiator: A Proactive Chatbot with Personalized Topic RAG for Enhancing Willingness to Converse

Topic-Initiator: A Proactive Chatbot with Personalized Topic RAG for Enhancing Willingness to Converse

Summary

Most chatbots wait for the user to choose what to talk about, which tires people out and erodes their motivation to keep chatting. Matsuo and colleagues at NTT's Human Informatics Labs address this with Topic-Initiator, a chatbot that opens each new session with a topic chosen for the individual user. The system runs a repeating cycle. After a conversation, an LLM turns the dialogue into web search queries and gathers candidate topics, and logs from other users' conversations are added to the pool. The proposed retrieval framework, Personalized-Topic RAG (PT-RAG), then sorts the candidates into categories such as travel or music. It also infers the user's interests and existing knowledge per category from past sessions. Finally, it asks an LLM to choose a category the user likes and, within it, an item the user probably does not know yet. Standard RAG favours content similar to earlier exchanges and so tends to repeat it. PT-RAG targets material that is both relevant and new. Automatic and human evaluations indicate that it finds novel, interesting content more accurately and makes users noticeably more willing to converse than the baselines.

Key points

  • PT-RAG has three components: (B-1) organizing candidates by topic category, (B-2) estimating the user's interests and knowledge per category, and (B-3) LLM-based selection of an unseen item from a category the user is interested in.
  • The paper poses two research questions: RQ1 asks whether category-constrained retrieval yields new and interesting topics, and RQ2 asks whether opening with such topics raises willingness to converse.
  • On the automatic side, the main RAG baseline is Zerhoudi (2025), a multi-agent reranking approach usable without training. Outputs are scored by an LLM judge with 1–10 prompts for novelty and interest.
  • The human study compares Topic-Initiator with a passive chatbot and a proactive chatbot that asks about previously disclosed events. In one example, the participant preferred the proactive bot at first but chose Topic-Initiator from the third session onward, because the other bot kept repeating itself.
  • The paper appears in the LREC 2026 proceedings, pages 19–34.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

Fields: Linguistics & languages

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.63317/5incc586qu8f

@inproceedings{matsuo2026topic,
  title = {{Topic-Initiator: A Proactive Chatbot with Personalized Topic RAG for Enhancing Willingness to Converse}},
  author = {Matsuo, Kazuya and Otsuka, Atsushi and Nomoto, Narichika and Nakatsuji, Makoto},
  booktitle = {Proceedings of the Fifteenth Language Resources and Evaluation Conference},
  year = {2026},
  doi = {10.63317/5incc586qu8f},
  url = {https://doi.org/10.63317/5incc586qu8f}
}

References

41 references, 1 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Sanghwan Bae, Donghyun Kwak, Soyoung Kang, Min Young Lee, Sungdong Kim, Yuin Jeong, Hyeri Kim, Sang-Woo Lee, Woomyoung Park, and Nako Sung. 2022. Keep me updated! memory management in long-term conversations. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 3769–3787. find
  2. Yi-Pei Chen, Noriki Nishida, Hideki Nakayama, and Yuji Matsumoto. 2024. Recent trends in personalized dialogue generation: A review of datasets, methodologies, and evaluations. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (… find
  3. Paul C Cozby. 1972. Self-disclosure, reciprocity and liking. Sociometry, pages 151–160. find
  4. Yashar Deldjoo, Zhankui He, Julian McAuley, Anton Korikov, Scott Sanner, Arnau Ramisa, René Vidal, Maheswaran Sathiamoorthy, Atoosa Kasirzadeh, and Silvia Milano. 2024. A review of modern recommender systems using generative models (gen-recsys). In Proceedings of the 30th ACM SIGKDD Conference on Kn… find
  5. Yang Deng, Wenqiang Lei, Wai Lam, and Tat-Seng Chua. 2023a. A survey on proactive dialogue systems: problems, methods, and prospects. In Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, pages 6583–6591. find
  6. Yang Deng, Lizi Liao, Liang Chen, Hongru Wang, Wenqiang Lei, and Tat-Seng Chua. 2023b. Prompting and evaluating large language models for proactive dialogues: Clarification, target-guided, and non-collaboration. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 10602–10… find
  7. Luke Friedman, Sameer Ahuja, David Allen, Zhenning Tan, Hakim Sidahmed, Changbo Long, Jun Xie, Gabriel Schubiner, Ajay Patel, Harsh Lara, et al. 2023. Leveraging large language models in conversational recommender systems. arXiv preprint arXiv:2305.07961. — [arXiv:2305.07961](https://arxiv.org/abs/2305.07961) find
  8. Shirley Anugrah Hayati, Dongyeop Kang, Qingxiaoyang Zhu, Weiyan Shi, and Zhou Yu. 2020. Inspired: Toward sociable recommendation dialog systems. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 8142– 8152. find
  9. Zhankui He, Zhouhang Xie, Rahul Jha, Harald Steck, Dawen Liang, Yesu Feng, Bodhisattwa Prasad Majumder, Nathan Kallus, and Julian McAuley. 2023. Large language models as zero-shot conversational recommenders. In Proceedings of the 32nd ACM international conference on information and knowledge manage… find
  10. Yerin Hwang, Yongil Kim, Yunah Jang, Jeesoo Bang, Hyunkyung Bae, and Kyomin Jung. 2024. Mp2d: An automated topic shift dialogue generation framework leveraging knowledge graphs. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 17682–17702. find
  11. Jihyoung Jang, Minseong Boo, and Hyounghun Kim. 2023. Conversation chronicles: Towards diverse temporal and relational dynamics in multi-session conversations. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 13584– 13606. find
  12. Wang-Cheng Kang, Jianmo Ni, Nikhil Mehta, Maheswaran Sathiamoorthy, Lichan Hong, Ed Chi, and Derek Zhiyuan Cheng. 2023. Do llms understand user preferences? evaluating llms on user rating prediction. arXiv preprint arXiv:2305.06474. — [arXiv:2305.06474](https://arxiv.org/abs/2305.06474) find
  13. Gibbeum Lee, Volker Hartmann, Jongho Park, Dimitris Papailiopoulos, and Kangwook Lee. 2023. Prompted llms as chatbot modules for long open-domain conversation. In Findings of the Association for Computational Linguistics: ACL 2023, pages 4536–4554. find
  14. Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich Küttler, Mike Lewis, Wen-tau Yih, Tim Rocktäschel, et al. 2020. Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in Neural Information Processing Systems, 33:9459–9474. find
  15. Siheng Li, Yichun Yin, Cheng Yang, Wangjie Jiang, Yiwei Li, Zesen Cheng, Lifeng Shang, Xin Jiang, Qun Liu, and Yujiu Yang. 2023. Newsdialogues: Towards proactive news grounded conversation. In Findings of the Association for Computational Linguistics: ACL 2023, pages 3634–3649. find
  16. Jungwoo Lim, Myunghoon Kang, Yuna Hur, Seung Won Jeong, Jinsung Kim, Yoonna Jang, Dongyub Lee, Hyesung Ji, Donghoon Shin, Seungryong Kim, et al. 2022. You truly understand what i need: Intellectual and friendly dialog agents grounding persona and knowledge. In Findings of the Association for Computa… find
  17. Junling Liu, Chao Liu, Peilin Zhou, Qichen Ye, Dading Chong, Kang Zhou, Yueqi Xie, Yuwei Cao, Shoujin Wang, Chenyu You, et al. 2023. Llmrec: Benchmarking large language models on recommendation task. arXiv preprint arXiv:2308.12241. — [arXiv:2308.12241](https://arxiv.org/abs/2308.12241) find
  18. Charles Packer, Vivian Fang, Shishir G Patil, Kevin Lin, Sarah Wooders, and Joseph E Gonzalez. 2023. Memgpt: Towards llms as operating systems. arXiv preprint arXiv:2310.08560. find
  19. Arjun Panickssery, Samuel Bowman, and Shi Feng. 2024. Llm evaluators recognize and favor their own generations. Advances in Neural Information Processing Systems, 37:68772– 68802. find
  20. Iryna Pentina, Tyler Hancock, and Tianling Xie. 2023. Exploring relationship development with social chatbots: A mixed-method study of replika. Computers in Human Behavior, 140:107600. find
  21. Scott Sanner, Krisztian Balog, Filip Radlinski, Ben Wedin, and Lucas Dixon. 2023. Large language models are competitive near cold-start recommenders for language-and item-based preferences. In Proceedings of the 17th ACM conference on recommender systems, pages 890– 896. find
  22. Damien Sileo, Wout Vossen, and Robbe Raymaekers. 2022. Zero-shot recommendation as language modeling. In European Conference on Information Retrieval, pages 223–230. Springer. find
  23. Charles Spearman. 1961. The proof and measurement of association between two things. find
  24. Jianheng Tang, Tiancheng Zhao, Chenyan Xiong, Xiaodan Liang, Eric P Xing, and Zhiting Hu. 2019. Target-guided open-domain conversation. Proceedings of the 57th Conference of the Association for Computational Linguistics, ACL 2019, pages 5624–5634. find
  25. Yuiko Tsunomori, Ryuichiro Higashinaka, Takeshi Yoshimura, and Yoshinori Isoda. 2021. Chat-oriented dialogue system that uses user information acquired through dialogue and its long-term evaluation. In Increasing Naturalness and Flexibility in Spoken Dialogue Interaction: 10th International Workshop… find
  26. Takahisa Uchida, Takashi Minato, and Hiroshi Ishiguro. 2024. Opinion attribution improves motivation to exchange subjective opinions with humanoid robots. Frontiers in Robotics and AI, 11:1175879. find
  27. Hongru Wang, Wenyu Huang, Yang Deng, Rui Wang, Zezhong Wang, Yufei Wang, Fei Mi, Jeff Z Pan, and Kam-Fai Wong. 2024. Unims-rag: A unified multi-source retrieval-augmented generation for personalized dialogue systems. arXiv preprint arXiv:2401.13256. — [arXiv:2401.13256](https://arxiv.org/abs/2401.13256) find
  28. Jian Wang, Yi Cheng, Dongding Lin, Chak Leong, and Wenjie Li. 2023a. Target-oriented proactive dialogue systems with personalization: Problem formulation and dataset curation. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1132–1143. find
  29. Jian Wang, Dongding Lin, and Wenjie Li. 2023b. Dialogue planning via brownian bridge stochastic process for goal-directed proactive dialogue. In Findings of the Association for Computational Linguistics: ACL 2023, pages 370–387. find
  30. Xiaolei Wang, Kun Zhou, Ji-Rong Wen, and Wayne Xin Zhao. 2022. Towards unified conversational recommender systems via knowledge-enhanced prompt learning. In Proceedings of the 28th ACM SIGKDD conference on knowledge discovery and data mining, pages 1929– 1937. find
  31. Wenquan Wu, Zhen Guo, Xiangyang Zhou, Hua Wu, Xiyuan Zhang, Rongzhong Lian, and Haifeng Wang. 2019. Proactive human-machine conversation with explicit conversation goal. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 3794–3804. find
  32. Huiyuan Xie, Zhenghao Liu, Chenyan Xiong, Zhiyuan Liu, and Ann Copestake. 2021. Tiage: A benchmark for topic-shift aware dialog modeling. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 1684– 1690. find
  33. Xinchao Xu, Zhibin Gou, Wenquan Wu, Zheng-Yu Niu, Hua Wu, Haifeng Wang, and Shihang Wang. 2022. Long time no see! open-domain conversation with long-term persona memory. In Findings of the Association for Computational Linguistics: ACL 2022, pages 2639–2650. find
  34. S Zerhoudi. 2025. Publication vi: Personarag: Enhancing retrieval-augmented generation systems with user-centric agents. User Simulation in Interactive Information Retrieval. find
  35. Qiang Zhang, Jason Naradowsky, and Yusuke Miyao. 2023. Mind the gap between conversations for improved long-term dialogue generation. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 10735– 10762. find
  36. Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li, Dacheng Li, Eric Xing, et al. 2023. Judging llm-as-a-judge with mt-bench and chatbot arena. Advances in Neural Information Processing Systems, 36:46595– 46623. find
  37. Hanxun Zhong, Zhicheng Dou, Yutao Zhu, Hongjin Qian, and Ji-Rong Wen. 2022. Less is more: Learning to refine dialogue history for personalized dialogue generation. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Tec… find
  38. Wanjun Zhong, Lianghong Guo, Qiqi Gao, He Ye, and Yanlin Wang. 2024. Memorybank: Enhancing large language models with long-term memory. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 38, pages 19724– 19731. find
  39. Yutao Zhu, Huaying Yuan, Shuting Wang, Jiongnan Liu, Wenhan Liu, Chenlong Deng, Haonan Chen, Zheng Liu, Zhicheng Dou, and Ji-Rong Wen. 2025. Large language models for information retrieval: A survey. ACM Transactions on Information Systems, 44(1):1–54. 7. find our card
  40. Language Resource References Hiroaki Sugiyama, Masahiro Mizukami, Tsunehiro Arimoto, Hiromi Narimatsu, Yuya Chiba, Hideharu Nakajima, and Toyomi Meguro. 2023. Empirical analysis of training strategies of transformer-based japanese chit-chat systems. In 2022 ieee spoken language technology workshop (… find
  41. Sanae Yamashita, Koji Inoue, Ao Guo, Shota Mochizuki, Tatsuya Kawahara, and Ryuichiro Higashinaka. 2023. RealPersonaChat: A realistic persona chat corpus with interlocutors’ own personalities. In Proceedings of the 37th Pacific Asia Conference on Language, Information and Computation, pages 852–861. find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/papers/matsuo-2026-topic-initiator-proactive-chatbot-personalized/