---
title: "METRO — paper by Yang et al. (2026) — summary and ideas"
description: "METRO replaces this with LLM-driven induction directly from raw human transcripts. 63 references."
authors: ["Haofu Yang", "Jiaji Liu", "Chen Huang", "Faguo Wu", "Wenqiang Lei", "See-Kiong Ng"]
year: 2026
venue: "Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2026.acl-long.978/"
doi: "10.18653/v1/2026.acl-long.978"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/yang-2026-metro-strategy-induction-expert-dialogue/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/yang-2026-metro-strategy-induction-expert-dialogue/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/41/) / METRO: Towards Strategy Induction from Expert Dialogue Transcripts for Non-collaborative Dialogues

# METRO: Towards Strategy Induction from Expert Dialogue Transcripts for Non-collaborative Dialogues

**Authors:** Haofu Yang, [Jiaji Liu](https://md.research.elamur.ai/free/en/authors/jiaji-liu/), [Chen Huang](https://md.research.elamur.ai/free/en/authors/chen-huang/), Faguo Wu, [Wenqiang Lei](https://md.research.elamur.ai/free/en/authors/wenqiang-lei/) and [See-Kiong Ng](https://md.research.elamur.ai/free/en/authors/see-kiong-ng/) · **Year:** 2026 · **Venue:** [Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.acl-long.978/) · [PDF](https://aclanthology.org/2026.acl-long.978.pdf) · [DOI 10.18653/v1/2026.acl-long.978](https://doi.org/10.18653/v1/2026.acl-long.978) · [OpenAlex](https://openalex.org/W7166815022)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
Agents for non-collaborative dialogue, such as price negotiation or donation persuasion, face a counterpart whose interests conflict with theirs, so they need sound strategies. These strategies have usually been hand-coded by domain experts who study transcripts and then paired with a separately trained planner, a costly pipeline that scales poorly. METRO replaces this with LLM-driven induction directly from raw human transcripts.

In an offline stage, METRO works through four steps:
- tags each expert turn with an action;
- enlarges the action inventory through LLM reflection over the whole dialogue;
- clusters dialogue histories into dialogue states;
- arranges the follow-up action sequences into trees, together forming a Strategy Forest.

In each tree, a root's immediate children give next-step tactics, while full branches encode longer-range plans. At inference, the agent matches the ongoing conversation to the closest tree. It then converts the top children and branches into short- and long-term guidance.

On two benchmarks, METRO beats competing approaches by roughly 9–10% on average. The induced strategies also transfer across tasks, which points to a cheaper and more scalable route to building strategic agents.

## Key points
- Evaluation uses the CraigslistBargain (CB) and PersuasionForGood (P4G) benchmarks, both built from human-human dialogues. Reported metrics include AT, SR and SL%. Baselines include PPDPP, GDP-zero and PRINCIPLES.
- METRO outperforms other strategy-induction methods by 10.24% on average across both benchmarks. The authors attribute the gain to more diverse actions and to planning foresight.
- The ablation removes expanded actions, Depth (long-term branches) and Breadth (short-term children). On P4G, removing any component reduces performance. On CB, dropping Depth actually helps, because the CB corpus yields redundant, low-diversity branches. This shows that results depend on transcript quality.
- In cross-task transfer, CB strategies carry over well to P4G, but the reverse direction is weaker. When the action space is enlarged, METRO remains robust, while most baselines degrade and MCTS-based GDP-zero becomes very expensive.
- Initial experiments suggest that LLM-generated transcripts can match or sometimes exceed human ones. A stated limitation is that the benchmark participants are probably ordinary users rather than professional negotiators or persuaders. Code: github.com/Humphrey-0125/METRO.

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

## Institutions

- [National University of Singapore](https://md.research.elamur.ai/free/en/universities/national-university-of-singapore/) — University, Singapore, Singapore · 207 works · 39,576 citations
- [Beihang University](https://md.research.elamur.ai/free/en/universities/beihang-university/) — University, Beijing, China · 86 works · 9,097 citations
- [Sichuan University](https://md.research.elamur.ai/free/en/universities/sichuan-university/) — University, Chengdu, China · 20 works · 1,293 citations
- [Nankai University](https://md.research.elamur.ai/free/en/universities/nankai-university/) — University, Tianjin, China · 36 works · 762 citations
- [Ministry of Education of the People's Republic of China](https://md.research.elamur.ai/free/en/government/ministry-of-education-of-the-people-s-republic-of-china/) — Government body, Beijing, China · 4 works · 117 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works

🧭 Topics (1): [🗨️ Dialogue systems](https://md.research.elamur.ai/free/en/topics/dialogue-systems/) · 654 works

## Cite

Cite as: Haofu Yang, Jiaji Liu, Chen Huang, Faguo Wu, Wenqiang Lei and See-Kiong Ng. 2026. METRO: Towards Strategy Induction from Expert Dialogue Transcripts for Non-collaborative Dialogues. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{yang2026metro,
  title = {{METRO: Towards Strategy Induction from Expert Dialogue Transcripts for Non-collaborative Dialogues}},
  author = {Haofu Yang, Jiaji Liu, Chen Huang, Faguo Wu, Wenqiang Lei and See-Kiong Ng},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.978},
  url = {https://doi.org/10.18653/v1/2026.acl-long.978}
}
```

- [← previous Metrical Revisions in the Ormulum Manuscript](https://md.research.elamur.ai/free/en/papers/cooper-2026-metrical-revisions-ormulum-manuscript/)
- [next → MEUR: A Benchmark for Evaluating Vision-Language Models on Multimodal Event Understanding and Reasoning](https://md.research.elamur.ai/free/en/papers/wang-2026-meur-benchmark-evaluating-vision-language/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/41/)

## References

63 references, 10 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Federico Bianchi, Patrick John Chia, Mert Yuksekgonul, Jacopo Tagliabue, Dan Jurafsky, and James Zou. 2024. How well can llms negotiate? negotiationarena platform and analysis. arXiv preprint arXiv:2402.05863. [find](https://scholar.google.com/scholar?q=Federico+Bianchi%2C+Patrick+John+Chia%2C+Mert+Yuksekgonul%2C+Jacopo+Tagliabue%2C+Dan+Jurafsky%2C+and+James+Zou%2E+2024%2E+How+well+can+llms+negotiate%3F+negotiationarena+platform+and+analysis%2E+arXiv+preprint+arXiv%3A24)
2. Helena Bonaldi, Sara Dellantonio, Serra Sinem Tekiroğlu, and Marco Guerini. 2022a. Human-machine collaboration approaches to build a dialogue dataset for hate speech countering. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 8031–8049, Abu Dhabi, Un… [find](https://scholar.google.com/scholar?q=Helena+Bonaldi%2C+Sara+Dellantonio%2C+Serra+Sinem+Tekirog%CC%86lu%2C+and+Marco+Guerini%2E+2022a%2E+Human%2Dmachine+collaboration+approaches+to+build+a+dialogue+dataset+for+hate+speech+countering%2E+In+Proceedings+of+the)
3. Helena Bonaldi, Sara Dellantonio, Serra Sinem Tekiroğlu, and Marco Guerini. 2022b. Human-machine collaboration approaches to build a dialogue dataset for hate speech countering. In Proceedings of the 2022 conference on empirical methods in natural language processing, pages 8031–8049. [find](https://scholar.google.com/scholar?q=Helena+Bonaldi%2C+Sara+Dellantonio%2C+Serra+Sinem+Tekirog%CC%86lu%2C+and+Marco+Guerini%2E+2022b%2E+Human%2Dmachine+collaboration+approaches+to+build+a+dialogue+dataset+for+hate+speech+countering%2E+In+Proceedings+of+the)
4. Sergio Burdisso, Srikanth Madikeri, and Petr Motlicek. 2024. Dialog2Flow: Pre-training soft-contrastive action-driven sentence embeddings for automatic dialog flow extraction. In Proceedings of the 2024 [find](https://scholar.google.com/scholar?q=Sergio+Burdisso%2C+Srikanth+Madikeri%2C+and+Petr+Motlicek%2E+2024%2E+Dialog2Flow%3A+Pre%2Dtraining+soft%2Dcontrastive+action%2Ddriven+sentence+embeddings+for+automatic+dialog+flow+extraction%2E+In+Proceedings+of+the+20)
5. Conference on Empirical Methods in Natural Language Processing, pages 5421–5440, Miami, Florida, USA. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Conference+on+Empirical+Methods+in+Natural+Language+Processing%2C+pages+5421%E2%80%935440%2C+Miami%2C+Florida%2C+USA%2E+Association+for+Computational+Linguistics%2E)
6. Chengkun Cai, Xu Zhao, Haoliang Liu, Zhongyu Jiang, Tianfang Zhang, Zongkai Wu, Jenq-Neng Hwang, and Lei Li. 2025. [The role of deductive and inductive reasoning in large language models](https://md.research.elamur.ai/free/en/papers/cai-2025-role-deductive-inductive-reasoning-large/). In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers…
7. Yue Chen, Chen Huang, Yang Deng, Wenqiang Lei, Dingnan Jin, Jia Liu, and Tat-Seng Chua. 2024. STYLE: Improving domain transferability of asking clarification questions in large language model powered conversational agents. In Findings of the Association for Computational Linguistics: ACL 2024, pages… [find](https://scholar.google.com/scholar?q=Yue+Chen%2C+Chen+Huang%2C+Yang+Deng%2C+Wenqiang+Lei%2C+Dingnan+Jin%2C+Jia+Liu%2C+and+Tat%2DSeng+Chua%2E+2024%2E+STYLE%3A+Improving+domain+transferability+of+asking+clarification+questions+in+large+language+model+powered+)
8. Prafulla Kumar Choubey, Xiangyu Peng, Shilpa Bhagavath, Caiming Xiong, Shiva Kumar Pentyala, and Chien-Sheng Wu. 2025. Turning conversations into workflows: A framework to extract and evaluate dialog workflows for service ai agents. arXiv preprint arXiv:2502.17321. [find](https://scholar.google.com/scholar?q=Prafulla+Kumar+Choubey%2C+Xiangyu+Peng%2C+Shilpa+Bhagavath%2C+Caiming+Xiong%2C+Shiva+Kumar+Pentyala%2C+and+Chien%2DSheng+Wu%2E+2025%2E+Turning+conversations+into+workflows%3A+A+framework+to+extract+and+evaluate+dialog+)
9. João Pedro Gandarela de Souza, Danilo Carvalho, and André Freitas. 2025. Inductive learning of logical theories with llms: A expressivity-graded analysis. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 39, pages 23752–23759. [find](https://scholar.google.com/scholar?q=Jo%C3%A3o+Pedro+Gandarela+de+Souza%2C+Danilo+Carvalho%2C+and+Andr%C3%A9+Freitas%2E+2025%2E+Inductive+learning+of+logical+theories+with+llms%3A+A+expressivity%2Dgraded+analysis%2E+In+Proceedings+of+the+AAAI+Conference+on+Arti)
10. Yang Deng, Wenqiang Lei, Minlie Huang, and Tat-Seng Chua. 2023a. Goal awareness for conversational AI: Proactivity, non-collaborativity, and beyond. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 6: Tutorial Abstracts), pages 1–10, Toronto, Canada.… [find](https://scholar.google.com/scholar?q=Yang+Deng%2C+Wenqiang+Lei%2C+Minlie+Huang%2C+and+Tat%2DSeng+Chua%2E+2023a%2E+Goal+awareness+for+conversational+AI%3A+Proactivity%2C+non%2Dcollaborativity%2C+and+beyond%2E+In+Proceedings+of+the+61st+Annual+Meeting+of+the+As)
11. Yang Deng, Wenqiang Lei, Minlie Huang, and Tat-Seng Chua. 2023b. Rethinking conversational agents in the era of llms: Proactivity, non-collaborativity, and beyond. In Proceedings of the Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific… [find](https://scholar.google.com/scholar?q=Yang+Deng%2C+Wenqiang+Lei%2C+Minlie+Huang%2C+and+Tat%2DSeng+Chua%2E+2023b%2E+Rethinking+conversational+agents+in+the+era+of+llms%3A+Proactivity%2C+non%2Dcollaborativity%2C+and+beyond%2E+In+Proceedings+of+the+Annual+Interna)
12. Yang Deng, Wenqiang Lei, Wai Lam, and Tat-Seng Chua. 2023c. A survey on proactive dialogue systems: Problems, methods, and prospects. arXiv preprint arXiv:2305.02750. — [arXiv:2305.02750](https://arxiv.org/abs/2305.02750) [find](https://scholar.google.com/scholar?q=Yang+Deng%2C+Wenqiang+Lei%2C+Wai+Lam%2C+and+Tat%2DSeng+Chua%2E+2023c%2E+A+survey+on+proactive+dialogue+systems%3A+Problems%2C+methods%2C+and+prospects%2E+arXiv+preprint+arXiv%3A2305%2E02750%2E+%E2%80%94+%5BarXiv%3A2305%2E02750%5D%28https%3A%2F%2Farxi)
13. Hanwen Du, Bo Peng, and Xia Ning. 2025. Planning with diffusion models for target-oriented dialogue systems. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 20307–20329, Vienna, Austria. Association for Computational Linguisti… [find](https://scholar.google.com/scholar?q=Hanwen+Du%2C+Bo+Peng%2C+and+Xia+Ning%2E+2025%2E+Planning+with+diffusion+models+for+target%2Doriented+dialogue+systems%2E+In+Proceedings+of+the+63rd+Annual+Meeting+of+the+Association+for+Computational+Linguistics+)
14. Ritam Dutt, Sayan Sinha, Rishabh Joshi, Surya Shekhar Chakraborty, Meredith Riggs, Xinru Yan, Hao-gang Bao, and Carolyn Penstein Rosé. 2021. Res-per: Computationally modelling resisting strategies in persuasive conversations. arXiv preprint arXiv:2101.10545. — [arXiv:2101.10545](https://arxiv.org/abs/2101.10545) [find](https://scholar.google.com/scholar?q=Ritam+Dutt%2C+Sayan+Sinha%2C+Rishabh+Joshi%2C+Surya+Shekhar+Chakraborty%2C+Meredith+Riggs%2C+Xinru+Yan%2C+Hao%2Dgang+Bao%2C+and+Carolyn+Penstein+Ros%C3%A9%2E+2021%2E+Res%2Dper%3A+Computationally+modelling+resisting+strategies+in+)
15. James D Finch, Yasasvi Josyula, and Jinho D Choi. 2025. Generative induction of dialogue task schemas with streaming refinement and simulated interactions. arXiv preprint arXiv:2504.18474. [find](https://scholar.google.com/scholar?q=James+D+Finch%2C+Yasasvi+Josyula%2C+and+Jinho+D+Choi%2E+2025%2E+Generative+induction+of+dialogue+task+schemas+with+streaming+refinement+and+simulated+interactions%2E+arXiv+preprint+arXiv%3A2504%2E18474%2E)
16. Marieke L Fransen, Edith G Smit, and Peeter WJ Ver-legh. 2015. Strategies and motives for resistance to persuasion: An integrative framework. Frontiers in psychology, 6:1201. [find](https://scholar.google.com/scholar?q=Marieke+L+Fransen%2C+Edith+G+Smit%2C+and+Peeter+WJ+Ver%2Dlegh%2E+2015%2E+Strategies+and+motives+for+resistance+to+persuasion%3A+An+integrative+framework%2E+Frontiers+in+psychology%2C+6%3A1201%2E)
17. Yao Fu, Hao Peng, Tushar Khot, and Mirella Lapata. 2023. [Improving language model negotiation with self-play and in-context learning from ai feedback](https://md.research.elamur.ai/free/en/papers/fu-2023-improving-language-model-negotiation-self/). Preprint, arXiv:2305.10142.
18. Lewis R Goldberg. 1992. The development of markers for the big-five factor structure. Psychological assessment, 4(1):26. [find](https://scholar.google.com/scholar?q=Lewis+R+Goldberg%2E+1992%2E+The+development+of+markers+for+the+big%2Dfive+factor+structure%2E+Psychological+assessment%2C+4%281%29%3A26%2E)
19. Michael E Gorman. 2002. Types of knowledge and their roles in technology transfer. The Journal of Technology Transfer, 27(3):219–231. [find](https://scholar.google.com/scholar?q=Michael+E+Gorman%2E+2002%2E+Types+of+knowledge+and+their+roles+in+technology+transfer%2E+The+Journal+of+Technology+Transfer%2C+27%283%29%3A219%E2%80%93231%2E)
20. James Gung, Raphael Shu, Emily Moeng, Wesley Rose, Salvatore Romeo, Arshit Gupta, Yassine Benajiba, Saab Mansour, and Yi Zhang. 2023. Intent induction from conversations for task-oriented dialogue track at DSTC 11. In Proceedings of the Eleventh Dialog System Technology Challenge, pages 242–259, Pra… [find](https://scholar.google.com/scholar?q=James+Gung%2C+Raphael+Shu%2C+Emily+Moeng%2C+Wesley+Rose%2C+Salvatore+Romeo%2C+Arshit+Gupta%2C+Yassine+Benajiba%2C+Saab+Mansour%2C+and+Yi+Zhang%2E+2023%2E+Intent+induction+from+conversations+for+task%2Doriented+dialogue+tra)
21. He He, Derek Chen, Anusha Balakrishnan, and Percy Liang. 2018. [Decoupling strategy and generation in negotiation dialogues](https://md.research.elamur.ai/free/en/papers/he-2018-decoupling-strategy-generation-negotiation-dialogues/). In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 2333–2343, Brussels, Belgium. Association for Computational Linguistics.
22. Yang Deng, Lizi Liao, Liang Chen, Hongru Wang, Wenqiang Lei, and Tat-Seng Chua. 2023d. [Prompting and evaluating large language models for proactive dialogues: Clarification, target-guided, and non-collaboration](https://md.research.elamur.ai/free/en/papers/deng-2023-prompting-evaluating-large-language-models/).
23. Tao He, Lizi Liao, Yixin Cao, Yuanxing Liu, Yiheng Sun, Zerui Chen, Ming Liu, and Bing Qin. 2025. Simulation-free hierarchical latent policy planning for proactive dialogues. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 39, pages 24032–24040. [find](https://scholar.google.com/scholar?q=Tao+He%2C+Lizi+Liao%2C+Yixin+Cao%2C+Yuanxing+Liu%2C+Yiheng+Sun%2C+Zerui+Chen%2C+Ming+Liu%2C+and+Bing+Qin%2E+2025%2E+Simulation%2Dfree+hierarchical+latent+policy+planning+for+proactive+dialogues%2E+In+Proceedings+of+the+AAA)
24. Yang Deng, Wenxuan Zhang, Wai Lam, See-Kiong Ng, and Tat-Seng Chua. 2024. Plug-and-play policy planner for large language model powered dialogue agents. The Twelfth International Conference on Learning Representations(ICLR). [find](https://scholar.google.com/scholar?q=Yang+Deng%2C+Wenxuan+Zhang%2C+Wai+Lam%2C+See%2DKiong+Ng%2C+and+Tat%2DSeng+Chua%2E+2024%2E+Plug%2Dand%2Dplay+policy+planner+for+large+language+model+powered+dialogue+agents%2E+The+Twelfth+International+Conference+on+Learnin)
25. Yikuan Hu, Chen Huang, and Wenqiang Lei. 2025. Astro: Automatic strategy optimization for non-cooperative dialogues. In Findings of the Association for Computational Linguistics: ACL 2025, pages 388–408. [find](https://scholar.google.com/scholar?q=Yikuan+Hu%2C+Chen+Huang%2C+and+Wenqiang+Lei%2E+2025%2E+Astro%3A+Automatic+strategy+optimization+for+non%2Dcooperative+dialogues%2E+In+Findings+of+the+Association+for+Computational+Linguistics%3A+ACL+2025%2C+pages+388%E2%80%934)
26. Chen Huang, Yiping Jin, Ilija Ilievski, Wenqiang Lei, and Jiancheng Lv. 2024a. Araida: Analogical reasoning-augmented interactive data annotation. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 10660–10675. [find](https://scholar.google.com/scholar?q=Chen+Huang%2C+Yiping+Jin%2C+Ilija+Ilievski%2C+Wenqiang+Lei%2C+and+Jiancheng+Lv%2E+2024a%2E+Araida%3A+Analogical+reasoning%2Daugmented+interactive+data+annotation%2E+In+Proceedings+of+the+62nd+Annual+Meeting+of+the+Asso)
27. Chen Huang, Peixin Qin, Yang Deng, Wenqiang Lei, Jiancheng Lv, and Tat-Seng Chua. 2024b. Concept – an evaluation protocol on conversational recommender systems with system-centric and user-centric factors. Preprint, arXiv:2404.03304. — [arXiv:2404.03304](https://arxiv.org/abs/2404.03304) [find](https://scholar.google.com/scholar?q=Chen+Huang%2C+Peixin+Qin%2C+Yang+Deng%2C+Wenqiang+Lei%2C+Jiancheng+Lv%2C+and+Tat%2DSeng+Chua%2E+2024b%2E+Concept+%E2%80%93+an+evaluation+protocol+on+conversational+recommender+systems+with+system%2Dcentric+and+user%2Dcentric+fac)
28. Chen Huang, Xinwei Yang, Yang Deng, Wenqiang Lei, JianCheng Lv, and Tat-Seng Chua. 2024c. Co-matching: Towards human-machine collaborative legal case matching. Preprint, arXiv:2405.10248. — [arXiv:2405.10248](https://arxiv.org/abs/2405.10248) [find](https://scholar.google.com/scholar?q=Chen+Huang%2C+Xinwei+Yang%2C+Yang+Deng%2C+Wenqiang+Lei%2C+JianCheng+Lv%2C+and+Tat%2DSeng+Chua%2E+2024c%2E+Co%2Dmatching%3A+Towards+human%2Dmachine+collaborative+legal+case+matching%2E+Preprint%2C+arXiv%3A2405%2E10248%2E+%E2%80%94+%5BarXiv%3A240)
29. Guangyuan Jiang, Manjie Xu, Song-Chun Zhu, Wenjuan Han, Chi Zhang, and Yixin Zhu. 2024. [Evaluating and inducing personality in pre-trained language models](https://md.research.elamur.ai/free/en/papers/jiang-2022-evaluating-inducing-personality-pre-trained/). Advances in Neural Information Processing Systems, 36.
30. Xinyi Jiang, Tianyi Hu, Yuheng Qin, Guoming Wang, Zhou Huan, Kehan Chen, Gang Huang, Rongxing Lu, and Siliang Tang. 2025. Chatmap: Mining human thought processes for customer service chatbots via multi-agent collaboration. In Findings of the Association for Computational Linguistics: ACL 2025, pages… [find](https://scholar.google.com/scholar?q=Xinyi+Jiang%2C+Tianyi+Hu%2C+Yuheng+Qin%2C+Guoming+Wang%2C+Zhou+Huan%2C+Kehan+Chen%2C+Gang+Huang%2C+Rongxing+Lu%2C+and+Siliang+Tang%2E+2025%2E+Chatmap%3A+Mining+human+thought+processes+for+customer+service+chatbots+via+mult)
31. Namyoung Kim, Kai Tzu-iunn Ong, Yeonjun Hwang, Minseok Kang, Iiseo Jihn, Gayoung Kim, Minju Kim, and Jinyoung Yeo. 2025a. Principles: Synthetic strategy memory for proactive dialogue agents. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 21329–21368. [find](https://scholar.google.com/scholar?q=Namyoung+Kim%2C+Kai+Tzu%2Diunn+Ong%2C+Yeonjun+Hwang%2C+Minseok+Kang%2C+Iiseo+Jihn%2C+Gayoung+Kim%2C+Minju+Kim%2C+and+Jinyoung+Yeo%2E+2025a%2E+Principles%3A+Synthetic+strategy+memory+for+proactive+dialogue+agents%2E+In+Findin)
32. Namyoung Kim, Kai Tzu-iunn Ong, Yeonjun Hwang, Minseok Kang, Iiseo Jihn, Gayoung Kim, Minju Kim, and Jinyoung Yeo. 2025b. PRINCIPLES: Synthetic strategy memory for proactive dialogue agents. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 21329–21368, Suzhou, China. A… [find](https://scholar.google.com/scholar?q=Namyoung+Kim%2C+Kai+Tzu%2Diunn+Ong%2C+Yeonjun+Hwang%2C+Minseok+Kang%2C+Iiseo+Jihn%2C+Gayoung+Kim%2C+Minju+Kim%2C+and+Jinyoung+Yeo%2E+2025b%2E+PRINCIPLES%3A+Synthetic+strategy+memory+for+proactive+dialogue+agents%2E+In+Findin)
33. Alice Lam. 2000. Tacit knowledge, organizational learning and societal institutions: An integrated framework. Organization studies, 21(3):487–513. [find](https://scholar.google.com/scholar?q=Alice+Lam%2E+2000%2E+Tacit+knowledge%2C+organizational+learning+and+societal+institutions%3A+An+integrated+framework%2E+Organization+studies%2C+21%283%29%3A487%E2%80%93513%2E)
34. Wenqiang Lei, Yao Zhang, Feifan Song, Hongru Liang, Jiaxin Mao, Jiancheng Lv, Zhenglu Yang, and Tat-Seng Chua. 2022. Interacting with non-cooperative user: A new paradigm for proactive dialogue policy. Preprint, arXiv:2204.07433. — [arXiv:2204.07433](https://arxiv.org/abs/2204.07433) [find](https://scholar.google.com/scholar?q=Wenqiang+Lei%2C+Yao+Zhang%2C+Feifan+Song%2C+Hongru+Liang%2C+Jiaxin+Mao%2C+Jiancheng+Lv%2C+Zhenglu+Yang%2C+and+Tat%2DSeng+Chua%2E+2022%2E+Interacting+with+non%2Dcooperative+user%3A+A+new+paradigm+for+proactive+dialogue+policy)
35. Jinggui Liang, Lizi Liao, Hao Fei, and Jing Jiang. 2024a. Synergizing large language models and pre-trained smaller models for conversational intent discovery. In Findings of the Association for Computational Linguistics ACL 2024, pages 14133–14147. [find](https://scholar.google.com/scholar?q=Jinggui+Liang%2C+Lizi+Liao%2C+Hao+Fei%2C+and+Jing+Jiang%2E+2024a%2E+Synergizing+large+language+models+and+pre%2Dtrained+smaller+models+for+conversational+intent+discovery%2E+In+Findings+of+the+Association+for+Compu)
36. Jinggui Liang, Yuxia Wu, Yuan Fang, Hao Fei, and Lizi Liao. 2024b. A survey of ontology expansion for conversational understanding. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 18111–18127, Miami, Florida, USA. Association for Computational Linguis… [find](https://scholar.google.com/scholar?q=Jinggui+Liang%2C+Yuxia+Wu%2C+Yuan+Fang%2C+Hao+Fei%2C+and+Lizi+Liao%2E+2024b%2E+A+survey+of+ontology+expansion+for+conversational+understanding%2E+In+Proceedings+of+the+2024+Conference+on+Empirical+Methods+in+Natura)
37. Leqi Liu, Rastogi Charvi, Holstein Ken, and Heidari Hoda. 2022. A taxonomy characterizing human and ml predictive decision-making. ICML Workshop on Human-Machine Collaboration and Teaming. [find](https://scholar.google.com/scholar?q=Leqi+Liu%2C+Rastogi+Charvi%2C+Holstein+Ken%2C+and+Heidari+Hoda%2E+2022%2E+A+taxonomy+characterizing+human+and+ml+predictive+decision%2Dmaking%2E+ICML+Workshop+on+Human%2DMachine+Collaboration+and+Teaming%2E)
38. Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. [Roberta: A robustly optimized bert pretraining approach](https://md.research.elamur.ai/free/en/papers/liu-2019-roberta-robustly-optimized-bert-pretraining/). arXiv preprint arXiv:1907.11692.
39. Zhaocheng Liu, Quan Tu, Wen Ye, Yu Xiao, Zhishou Zhang, Hengfu Cui, Yalun Zhu, Qiang Ju, Shizheng Li, and Jian Xie. 2025. Exploring the inquiry-diagnosis relationship with advanced patient simulators. arXiv preprint arXiv:2501.09484. — [arXiv:2501.09484](https://arxiv.org/abs/2501.09484) [find](https://scholar.google.com/scholar?q=Zhaocheng+Liu%2C+Quan+Tu%2C+Wen+Ye%2C+Yu+Xiao%2C+Zhishou+Zhang%2C+Hengfu+Cui%2C+Yalun+Zhu%2C+Qiang+Ju%2C+Shizheng+Li%2C+and+Jian+Xie%2E+2025%2E+Exploring+the+inquiry%2Ddiagnosis+relationship+with+advanced+patient+simulators%2E)
40. Ryan Louie, Ananjan Nandi, William Fang, Cheng Chang, Emma Brunskill, and Diyi Yang. 2024. [Roleplay-doh: Enabling domain-experts to create LLM-simulated patients via eliciting and adhering to principles](https://md.research.elamur.ai/free/en/papers/louie-2024-roleplay-doh-enabling-domain-experts/). In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages…
41. Ikujiro Nonaka. 1994. A dynamic theory of organizational knowledge creation. Organization science, 5(1):14–37. [find](https://scholar.google.com/scholar?q=Ikujiro+Nonaka%2E+1994%2E+A+dynamic+theory+of+organizational+knowledge+creation%2E+Organization+science%2C+5%281%29%3A14%E2%80%9337%2E)
42. Jiao Ou, Jiayu Wu, Che Liu, Fuzheng Zhang, Di Zhang, and Kun Gai. 2024. Inductive-deductive strategy reuse for multi-turn instructional dialogues. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 17402– 17431. [find](https://scholar.google.com/scholar?q=Jiao+Ou%2C+Jiayu+Wu%2C+Che+Liu%2C+Fuzheng+Zhang%2C+Di+Zhang%2C+and+Kun+Gai%2E+2024%2E+Inductive%2Ddeductive+strategy+reuse+for+multi%2Dturn+instructional+dialogues%2E+In+Proceedings+of+the+2024+Conference+on+Empirical+Me)
43. Connor Pryor, Quan Yuan, Jeremiah Liu, Mehran Kazemi, Deepak Ramachandran, Tania Bedrax-Weiss, and Lise Getoor. 2023. Using domain knowledge to guide dialog structure induction via neural probabilistic soft logic. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguis… [find](https://scholar.google.com/scholar?q=Connor+Pryor%2C+Quan+Yuan%2C+Jeremiah+Liu%2C+Mehran+Kazemi%2C+Deepak+Ramachandran%2C+Tania+Bedrax%2DWeiss%2C+and+Lise+Getoor%2E+2023%2E+Using+domain+knowledge+to+guide+dialog+structure+induction+via+neural+probabilisti)
44. Maarten De Raedt, Fréderic Godin, Chris Develder, and Thomas Demeester. 2024. Revisiting clustering for efficient unsupervised dialogue structure induction. Applied Intelligence, 54(7):5278–5305. [find](https://scholar.google.com/scholar?q=Maarten+De+Raedt%2C+Fr%C3%A9deric+Godin%2C+Chris+Develder%2C+and+Thomas+Demeester%2E+2024%2E+Revisiting+clustering+for+efficient+unsupervised+dialogue+structure+induction%2E+Applied+Intelligence%2C+54%287%29%3A5278%E2%80%935305%2E)
45. Gilbert Ryle. 1945. Knowing how and knowing that: The presidential address. In Proceedings of the Aristotelian society, volume 46, pages 1–16. JSTOR. [find](https://scholar.google.com/scholar?q=Gilbert+Ryle%2E+1945%2E+Knowing+how+and+knowing+that%3A+The+presidential+address%2E+In+Proceedings+of+the+Aristotelian+society%2C+volume+46%2C+pages+1%E2%80%9316%2E+JSTOR%2E)
46. Susanne G Scott and Reginald A Bruce. 1995. Decision-making style: The development and assessment of a new measure. Educational and psychological measurement, 55(5):818–831. [find](https://scholar.google.com/scholar?q=Susanne+G+Scott+and+Reginald+A+Bruce%2E+1995%2E+Decision%2Dmaking+style%3A+The+development+and+assessment+of+a+new+measure%2E+Educational+and+psychological+measurement%2C+55%285%29%3A818%E2%80%93831%2E)
47. Weiyan Shi, Kun Qian, Xuewei Wang, and Zhou Yu. 2019. How to build user simulators to train rl-based dialog systems. arXiv preprint arXiv:1909.01388. [find](https://scholar.google.com/scholar?q=Weiyan+Shi%2C+Kun+Qian%2C+Xuewei+Wang%2C+and+Zhou+Yu%2E+2019%2E+How+to+build+user+simulators+to+train+rl%2Dbased+dialog+systems%2E+arXiv+preprint+arXiv%3A1909%2E01388%2E)
48. David Silver, Aja Huang, Chris J Maddison, Arthur Guez, Laurent Sifre, George Van Den Driessche, Julian Schrittwieser, Ioannis Antonoglou, Veda Panneershelvam, Marc Lanctot, and 1 others. 2016. Mastering the game of go with deep neural networks and tree search. nature, 529(7587):484–489. [find](https://scholar.google.com/scholar?q=David+Silver%2C+Aja+Huang%2C+Chris+J+Maddison%2C+Arthur+Guez%2C+Laurent+Sifre%2C+George+Van+Den+Driessche%2C+Julian+Schrittwieser%2C+Ioannis+Antonoglou%2C+Veda+Panneershelvam%2C+Marc+Lanctot%2C+and+1+others%2E+2016%2E+Master)
49. Philipp Spitzer, Niklas Kühl, and Marc Goutier. 2022. Training novices: The role of human-ai collaboration and knowledge transfer. In Workshop on Human-Machine Collaboration and Teaming (HM-CaT 2022), 23rd July, Baltimore. [find](https://scholar.google.com/scholar?q=Philipp+Spitzer%2C+Niklas+K%C3%BChl%2C+and+Marc+Goutier%2E+2022%2E+Training+novices%3A+The+role+of+human%2Dai+collaboration+and+knowledge+transfer%2E+In+Workshop+on+Human%2DMachine+Collaboration+and+Teaming+%28HM%2DCaT+2022%29%2C)
50. Renato Vukovic, David Arps, Carel van Niekerk, Benjamin Matthias Ruppik, Hsien-Chin Lin, Michael Heck, and Milica Gasic. 2024. Dialogue ontology relation extraction via constrained chain-of-thought decoding. In Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dia… [find](https://scholar.google.com/scholar?q=Renato+Vukovic%2C+David+Arps%2C+Carel+van+Niekerk%2C+Benjamin+Matthias+Ruppik%2C+Hsien%2DChin+Lin%2C+Michael+Heck%2C+and+Milica+Gasic%2E+2024%2E+Dialogue+ontology+relation+extraction+via+constrained+chain%2Dof%2Dthought+de)
51. Borui Wang, Kathleen McKeown, and Rex Ying. 2025a. Dystil: Dynamic strategy induction with large language models for reinforcement learning. arXiv preprint arXiv:2505.03209. — [arXiv:2505.03209](https://arxiv.org/abs/2505.03209) [find](https://scholar.google.com/scholar?q=Borui+Wang%2C+Kathleen+McKeown%2C+and+Rex+Ying%2E+2025a%2E+Dystil%3A+Dynamic+strategy+induction+with+large+language+models+for+reinforcement+learning%2E+arXiv+preprint+arXiv%3A2505%2E03209%2E+%E2%80%94+%5BarXiv%3A2505%2E03209%5D%28https)
52. Haiyang Wang, Zhiliang Tian, Yuchen Pan, Xin Song, Xin Niu, Minlie Huang, and Bin Zhou. 2025b. Battling against tough resister: Strategy planning with adversarial game for non-collaborative dialogues. In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume… [find](https://scholar.google.com/scholar?q=Haiyang+Wang%2C+Zhiliang+Tian%2C+Yuchen+Pan%2C+Xin+Song%2C+Xin+Niu%2C+Minlie+Huang%2C+and+Bin+Zhou%2E+2025b%2E+Battling+against+tough+resister%3A+Strategy+planning+with+adversarial+game+for+non%2Dcollaborative+dialogues%2E)
53. Xuewei Wang, Weiyan Shi, Richard Kim, Yoojung Oh, Sijia Yang, Jingwen Zhang, and Zhou Yu. 2019. [Persuasion for good: Towards a personalized persuasive dialogue system for social good](https://md.research.elamur.ai/free/en/papers/wang-2019-persuasion-good-personalized-persuasive-dialogue/). In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 5635–5649, Florenc…
54. Edwin B Wilson. 1927. Probable inference, the law of succession, and statistical inference. Journal of the American Statistical Association, 22(158):209–212. [find](https://scholar.google.com/scholar?q=Edwin+B+Wilson%2E+1927%2E+Probable+inference%2C+the+law+of+succession%2C+and+statistical+inference%2E+Journal+of+the+American+Statistical+Association%2C+22%28158%29%3A209%E2%80%93212%2E)
55. Shitao Xiao, Zheng Liu, Peitian Zhang, and Niklas Muennighoff. 2023. [C-pack: Packaged resources to advance general chinese embedding](https://md.research.elamur.ai/free/en/papers/xiao-2023-c-pack-packed-resources/). Preprint, arXiv:2309.07597.
56. Zhouhang Xie, Bodhisattwa Prasad Majumder, Mengjie Zhao, Yoshinori Maeda, Keiichi Yamada, Hiromi Wakaki, and Julian McAuley. 2024. Few-shot dialogue strategy learning for motivational interviewing via inductive reasoning. In Findings of the Association for Computational Linguistics ACL 2024, pages 1… [find](https://scholar.google.com/scholar?q=Zhouhang+Xie%2C+Bodhisattwa+Prasad+Majumder%2C+Mengjie+Zhao%2C+Yoshinori+Maeda%2C+Keiichi+Yamada%2C+Hiromi+Wakaki%2C+and+Julian+McAuley%2E+2024%2E+Few%2Dshot+dialogue+strategy+learning+for+motivational+interviewing+via)
57. Xiao Yu, Maximillian Chen, and Zhou Yu. 2023. Prompt-based Monte-Carlo tree search for goal-oriented dialogue policy planning. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 7101–7125, Singapore. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Xiao+Yu%2C+Maximillian+Chen%2C+and+Zhou+Yu%2E+2023%2E+Prompt%2Dbased+Monte%2DCarlo+tree+search+for+goal%2Doriented+dialogue+policy+planning%2E+In+Proceedings+of+the+2023+Conference+on+Empirical+Methods+in+Natural+Lan)
58. Haolan Zhan, Yufei Wang, Tao Feng, Yuncheng Hua, Suraj Sharma, Zhuang Li, Lizhen Qu, Zhaleh Semnani Azad, Ingrid Zukerman, and Gholamreza Haffari. 2024. Let’s negotiate! a survey of negotiation dialogue systems. arXiv preprint arXiv:2402.01097. [find](https://scholar.google.com/scholar?q=Haolan+Zhan%2C+Yufei+Wang%2C+Tao+Feng%2C+Yuncheng+Hua%2C+Suraj+Sharma%2C+Zhuang+Li%2C+Lizhen+Qu%2C+Zhaleh+Semnani+Azad%2C+Ingrid+Zukerman%2C+and+Gholamreza+Haffari%2E+2024%2E+Let%E2%80%99s+negotiate%21+a+survey+of+negotiation+dialog)
59. Tong Zhang, Chen Huang, Yang Deng, Hongru Liang, Jia Liu, Zujie Wen, Wenqiang Lei, and Tat-Seng Chua. 2024a. Strength lies in differences! improving strategy planning for non-collaborative dialogues via diversified user simulation. In Proceedings of the 2024 Conference on Empirical Methods in Natura… [find](https://scholar.google.com/scholar?q=Tong+Zhang%2C+Chen+Huang%2C+Yang+Deng%2C+Hongru+Liang%2C+Jia+Liu%2C+Zujie+Wen%2C+Wenqiang+Lei%2C+and+Tat%2DSeng+Chua%2E+2024a%2E+Strength+lies+in+differences%21+improving+strategy+planning+for+non%2Dcollaborative+dialogues+v)
60. Tong Zhang, Junhong Liu, Chen Huang, Jia Liu, Hongru Liang, Zujie Wen, and Wenqiang Lei. 2023. Towards effective automatic debt collection with persona awareness. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 32–45, Singapore. Associ… [find](https://scholar.google.com/scholar?q=Tong+Zhang%2C+Junhong+Liu%2C+Chen+Huang%2C+Jia+Liu%2C+Hongru+Liang%2C+Zujie+Wen%2C+and+Wenqiang+Lei%2E+2023%2E+Towards+effective+automatic+debt+collection+with+persona+awareness%2E+In+Proceedings+of+the+2023+Conference)
61. Tong Zhang, Peixin Qin, Yang Deng, Chen Huang, Wenqiang Lei, Junhong Liu, Dingnan Jin, Hongru Liang, and Tat-Seng Chua. 2024b. [CLAMBER: A benchmark of identifying and clarifying ambiguous information needs in large language models](https://md.research.elamur.ai/free/en/papers/zhang-2024-clamber-benchmark-identifying-clarifying-ambiguous/). In Proceedings of the 62nd Annual Meeting of the Association for Com…
62. Yiheng Zhou, He He, Alan W Black, and Yulia Tsvetkov. 2019a. A dynamic strategy coach for effective negotiation. In Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue, pages 367–378, Stockholm, Sweden. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Yiheng+Zhou%2C+He+He%2C+Alan+W+Black%2C+and+Yulia+Tsvetkov%2E+2019a%2E+A+dynamic+strategy+coach+for+effective+negotiation%2E+In+Proceedings+of+the+20th+Annual+SIGdial+Meeting+on+Discourse+and+Dialogue%2C+pages+367%E2%80%93)
63. Yiheng Zhou, Yulia Tsvetkov, Alan W Black, and Zhou Yu. 2019b. Augmenting non-collaborative dialog systems with explicit semantic and strategic dialog history. Preprint, arXiv:1909.13425. — [arXiv:1909.13425](https://arxiv.org/abs/1909.13425) [find](https://scholar.google.com/scholar?q=Yiheng+Zhou%2C+Yulia+Tsvetkov%2C+Alan+W+Black%2C+and+Zhou+Yu%2E+2019b%2E+Augmenting+non%2Dcollaborative+dialog+systems+with+explicit+semantic+and+strategic+dialog+history%2E+Preprint%2C+arXiv%3A1909%2E13425%2E+%E2%80%94+%5BarXiv%3A190)

*Updated 2 November 2026*