Elamur Research⌕
☰
home / papers / 2024 / Decision-Oriented Dialogue for Human-AI Collaboration

Decision-Oriented Dialogue for Human-AI Collaboration

Paper · 2024 · Jessy Lin, Nicholas Tomlin, Jacob Andreas et al.

Summary

The paper argues that many daily choices, such as booking group travel or matching reviewers to papers, are hard optimization problems. In these problems an AI system and the people it helps each hold only part of the needed knowledge. The authors define "decision-oriented dialogue" (DoD): agents talk in natural language to agree on a joint decision. They model it as a Dec-POMDP over a weighted graph, with a graded reward for decision quality minus a cost for communication. They build three domains: Assignment (two co-chairs matching reviewers to papers), Planning (an assistant helping a user build a city itinerary) and Mediation (an assistant reconciling travel plans for several users). These are released as DialOp, an open-source suite with procedurally generated game instances, human interfaces and text environments. Human-human dialogues provide a reference point. In evaluations with people, in self-play and in a new prompted self-play setup, GPT-3 reaches clearly lower rewards than human assistants, even though its conversations run longer. This makes DialOp a testbed for agents that must reason, optimize and communicate efficiently.

Key points

  • The task formalism has the following parts:
    • a fixed world state shown as a weighted graph;
    • partial observations for each agent;
    • natural-language messages plus formal propose, accept and reject actions;
    • a linear reward over the chosen subgraph, normalized to [0, 1].
  • The three domains are Assignment, Planning and Mediation. Each has a GUI for collecting human data and an OpenAI Gym-like text environment for language models.
  • The collected human-human dialogues average about 13 messages and roughly 8 minutes each.
  • GPT-3 was benchmarked with humans, in self-play, and in prompted self-play, where models finish partial human dialogues. It underperforms human assistants in all task settings.
  • Dialogues, environments and interfaces are released at github.com/jlin816/dialop.

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

🏢MicrosoftRedmond · United States325 works · 142,931 citations🎓University of California, BerkeleyBerkeley · United States175 works · 227,440 citations

 Fields, topics and concepts

📚 Shelves 4The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArtificial Intelligence · 16,194 worksArts and Humanities · 16,039 worksLanguage and Linguistics · 15,891 works

🧭 Topics 1Research subjects and languages the work is about.Dialogue systems · 624 works

Cite

Cite as Jessy Lin, Nicholas Tomlin, Jacob Andreas and Jason Eisner. 2024. Decision-Oriented Dialogue for Human-AI Collaboration. Transactions of the Association for Computational Linguistics.

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.1162/tacl_a_00679

@article{lin2024decision,
  title = {{Decision-Oriented Dialogue for Human-AI Collaboration}},
  author = {Jessy Lin, Nicholas Tomlin, Jacob Andreas and Jason Eisner},
  journal = {Transactions of the Association for Computational Linguistics},
  year = {2024},
  doi = {10.1162/tacl\_a\_00679},
  url = {https://doi.org/10.1162/tacl_a_00679}
}

References

42 references, 16 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. James F. Allen and George Ferguson. 2002. Human-machine collaborative planning. In Proceedings of the 2002 Workshop on Knowledge and Reasoning in Practical Dialogue Systems. Edinburgh, Scotland. International Joint Conferences on Artificial Intelligence Organization. find
  2. James F. Allen, Lenhart K. Schubert, George Ferguson, Peter Heeman, Chung Hee Hwang, Tsuneaki Kato, Marc Light, Nathaniel Martin, Bradford Miller, Massimo Poesio, and David Traum. 1995. The TRAINS project: A case study in building a conversational planning agent. Journal of Experimental & Theoretica… — [doi:10.1080/09528139508953799](https://doi.org/10.1080/09528139508953799) find
  3. Anton Bakhtin, Noam Brown, Emily Dinan, Gabriele Farina, Colin Flaherty, Daniel Fried, Andrew Goff, Jonathan Gray, Hengyuan Hu, Athul Paul Jacob, Mojtaba Komeili, Karthik Konath, Minae Kwon, Adam Lerer, Mike Lewis, Alexander H. Miller, Sasha Mitts, Adithya Renduchintala, Stephen Roller, Dirk Rowe, W… find
  4. Nolan Bard, Jakob N. Foerster, Sarath Chandar, Neil Burch, Marc Lanctot, H. Francis Song, Emilio Parisotto, Vincent Dumoulin, Subhodeep Moitra, Edward Hughes, Iain Dunning, Shibl Mourad, Hugo Larochelle, Marc G. Bellemare, and Michael Bowling. 2020. The Hanabi challenge: A new frontier for AI resear… — [doi:10.1016/j.artint](https://doi.org/10.1016/j.artint) find
  5. In Advances in Neural Information Processing Systems (NeurIPS), volume 32. Curran Associates, Inc. find
  6. Daniel S. Bernstein, Shlomo Zilberstein, and Neil Immerman. 2000. The complexity of decentralized control of Markov decision processes. In Proceedings of the Sixteenth Conference on Uncertainty in Artificial Intelligence (UAI), UAI’00, pages 32–37, San Francisco, CA, USA. Morgan Kaufmann Publishers… find
  7. Laurent Charlin and Richard S. Zemel. 2013. The Toronto paper matching system: An automated paper-reviewer assignment system. In Proceedings of the ICML Workshop on Peer Reviewing and Publishing Models (PEER). find
  8. Aakanksha Chowdhery, Sharan Narang, Jacob Devlin, Maarten Bosma, Gaurav Mishra, Adam Roberts, Paul Barham, Hyung Won Chung, Charles Sutton, Sebastian Gehrmann, Parker Schuh, Kensen Shi, Sasha Tsvyashchenko, Joshua Maynez, Abhishek Rao, Parker Barnes, Yi Tay, Noam Shazeer, Vinodkumar Prabhakaran, Emi… — PaLM: Scaling Language Modeling with Pathways
  9. Greg Brockman, Vicki Cheung, Ludwig Pettersson, Jonas Schneider, John Schulman, Jie Tang, and Wojciech Zaremba. 2016. OpenAI Gym. find
  10. Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D. Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel Ziegler, Jeffrey Wu, Clemens Winter, Chr… — Language Models are Few-Shot Learners
  11. Paweł Budzianowski, Tsung-Hsien Wen, Bo-Hsiang Tseng, Iñigo Casanueva, Stefan Ultes, Osman Ramadan, and Milica Gašić. 2018. MultiWOZ—A large-scale multi-domain Wizard-of-Oz dataset for task-oriented dialogue modelling. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language…
  12. Giuseppe Carenini and Johanna D. Moore. 2006. Generating and evaluating evaluative arguments. Artificial Intelligence, 170(11):925–952. https://doi.org/10.1016/j.artint .2006.05.003 — [doi:10.1016/j.artint](https://doi.org/10.1016/j.artint) ↗
  13. Micah Carroll, Rohin Shah, Mark K. Ho, Tom Griffiths, Sanjit Seshia, Pieter Abbeel, and Anca Dragan. 2019. On the utility of learning about humans for human-AI coordination. find
  14. Allan Dafoe, Edward Hughes, Yoram Bachrach, Tantum Collins, Kevin R. McKee, Joel Z. Leibo, K. Larson, and Thore Graepel. 2020. Open problems in cooperative AI. Computing Research Repository (CoRR), arXiv:2012 .08630. find
  15. Daniel Fried, Nicholas Tomlin, Jennifer Hu, Roma Patel, and Aida Nematzadeh. 2023. Pragmatics in language grounding: Phenomena, tasks, and modeling approaches. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 12619–12640, Singapore. Association for Computational Lingui…
  16. Dylan Hadfield-Menell, Stuart J. Russell, Pieter Abbeel, and Anca Dragan. 2016. Cooperative inverse reinforcement learning. In Advances in Neural Information Processing Systems (NeurIPS), volume 29. Curran Associates, Inc. find
  17. He He, Anusha Balakrishnan, Mihail Eric, and Percy Liang. 2017. Learning symmetric collaborative dialogue agents with dynamic knowledge graph embeddings. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (ACL), pages 1766–1776, Vancouv… find
  18. Ruderman, Nicolas Sonnerat, Tim Green, Louise Deason, Joel Z. Leibo, David Silver, Demis Hassabis, Koray Kavukcuoglu, and Thore Graepel. 2019. Human-level performance in 3D multiplayer games with population-based reinforcement learning. Science, 364(6443):859–865. https://doi .org/10.1126/science.aa… find
  19. Hong Jun Jeon, Smitha Milli, and Anca Dragan. 2020. Reward-rational (implicit) choice: A unifying formalism for reward learning. In Advances in Neural Information Processing Systems (NeurIPS), volume 33, pages 4415–4426. Curran Associates, Inc. find
  20. Xiaohui Kong and Christian D. Schunn. 2007. Global vs. local information processing in visual/spatial problem solving: The case of traveling salesman problem. Cognitive Systems Research, 8(3):192–207. https://doi.org/10.1016/j.cogsys.2007.06.002 — [doi:10.1016/j.cogsys.2007.06.002](https://doi.org/10.1016/j.cogsys.2007.06.002) ↗
  21. He He, Derek Chen, Anusha Balakrishnan, and Percy Liang. 2018. Decoupling strategy and generation in negotiation dialogues. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 2333–2343, Brussels, Belgium. Association for Computational Linguistics…
  22. Mike Lewis, Denis Yarats, Yann Dauphin, Devi Parikh, and Dhruv Batra. 2017. Deal or no deal? End-to-end learning of negotiation dialogues. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 2443–2453, Copenhagen, Denmark. Association for Computat…
  23. Johannes Heinrich, Marc Lanctot, and David Silver. 2015. Fictitious self-play in extensive-form games. In Proceedings of the 32nd International Conference on Machine Learning (ICML), volume 37 of Proceedings of Machine Learning Research, pages 805–813. Lille, France. find
  24. Belinda Z. Li, Maxwell Nye, and Jacob Andreas. 2021. Implicit representations of meaning in neural language models. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Pa… find
  25. Dan Hendrycks, Collin Burns, Saurav Kadavath, Akul Arora, Steven Basart, Eric Tang, Dawn Song, and Jacob Steinhardt. 2021. Measuring mathematical problem solving with the MATH dataset. In Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks, volume 1.
  26. Eric Horvitz. 1999. Principles of mixed-initiative user interfaces. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, pages 159–166. https://doi.org/10.1145/302979.303030 — [doi:10.1145/302979.303030](https://doi.org/10.1145/302979.303030) ↗
  27. Jiwei Li, Will Monroe, Alan Ritter, Dan Jurafsky, Michel Galley, and Jianfeng Gao. 2016. Deep reinforcement learning for dialogue generation. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1192–1202, Austin, Texas. Association for Computation…
  28. Max Jaderberg, Wojciech M. Czarnecki, Iain Dunning, Luke Marris, Guy Lever, Antonio Garcia Castañeda, Charles Beattie, Neil C. Rabinowitz, Ari S. Morcos, Avraham Jessy Lin, Daniel Fried, Dan Klein, and Anca Dragan. 2022. Inferring rewards from language in context. In Proceedings of the 60th Annual… find
  29. David G. Novick and Stephen Sutton. 1997. What is mixed-initiative interaction? In Proceedings of the AAAI Spring Symposium on Computational Models for Mixed Initiative Interaction, volume 2, page 12. find
  30. Maxwell I. Nye, Anders Johan Andreassen, Guy Gur-Ari, Henryk Michalewski, Jacob Austin, David Bieber, David Dohan, Aitor Lewkowycz, Maarten Bosma, David Luan, Charles Sutton, and Augustus Odena. 2021. Show your work: Scratchpads for intermediate computation with language models. Computing Research R…
  31. Timo Schick, Jane Dwivedi-Yu, Roberto Dessi, Roberta Raileanu, Maria Lomeli, Eric Hambro, Luke Zettlemoyer, Nicola Cancedda, and Thomas Scialom. 2023. Toolformer: Language models can teach themselves to use tools. In Advances in Neural Information Processing Systems, volume 36, pages 68539–68551. Cu…
  32. David Schlangen. 2019. Grounded agreement games: Emphasizing conversational grounding in visual dialogue settings. Computing Research Repository (CoRR), arXiv:1908.11279. — [arXiv:1908.11279](https://arxiv.org/abs/1908.11279) find
  33. Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, John Schulman, Jacob Hilton, Fraser Kelton, Luke Miller, Maddie Simens, Amanda Askell, Peter Welinder, Paul F. Christiano, Jan Leike, and Ryan Lowe. 2022. Tr… — Training language models to follow instructions with human feedback
  34. John W. Payne, James R. Bettman, and David A. Schkade. 1999. Measuring constructed preferences: Towards a building code. Journal of Risk and Uncertainty, 19(1/3):243–270. https://doi.org/10.1023/A:1007843931054 — [doi:10.1023/a:1007843931054](https://doi.org/10.1023/a:1007843931054) ↗
  35. Christopher Potts. 2012. Goal-driven answers in the Cards dialogue corpus. In Proceedings of the 30th West Coast Conference on Formal Linguistics (WCCFL), pages 1–20. Cascadilla Proceedings Project. find
  36. Semantic Machines, Jacob Andreas, John Bufe, David Burkett, Charles Chen, Josh Clausman, Jean Crawford, Kate Crim, Jordan DeLoach, Leah Dorner, Jason Eisner, Hao Fang, Alan Guo, David Hall, Kristin Hayes, Kellie Hill, Diana Ho, Wendy Iwaszuk, Smriti Jha, Dan Klein, Jayant Krishnamurthy, Theo Lanman,… — Task-Oriented Dialogue as Dataflow Synthesis
  37. Andreas Stolcke, Klaus Ries, Noah Coccaro, Elizabeth Shriberg, Rebecca Bates, Daniel Jurafsky, Paul Taylor, Rachel Martin, Carol Van Ess-Dykema, and Marie Meteer. 2000. Dialogue act modeling for automatic tagging and recognition of conversational speech. Computational Linguistics, 26(3):339–374. htt…
  38. Dorsa Sadigh, Shankar Sastry, Sanjit A. Seshia, and Anca D. Dragan. 2016. Planning for autonomous cars that leverage effects on human actions. In Proceedings of Robotics: Science and Systems (RSS). Ann Arbor, Michigan. find
  39. D. J. Strouse, Kevin McKee, Matt Botvinick, Edward Hughes, and Richard Everett. 2021. Collaborating with humans without human Maarten Sap, Ronan Le Bras, Daniel Fried, and Yejin Choi. 2022. Neural theory-of-mind? data. In Advances in Neural Information Processing Systems (NeurIPS), volume 34, pages… find
  40. Alane Suhr, Claudia Yan, Jack Schluger, Stanley Yu, Hadi Khader, Marwa Mouallem, Iris Zhang, and Yoav Artzi. 2019. Executing instructions in situated collaborative interactions. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint…
  41. Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik R. Narasimhan, and Yuan Cao. 2023. ReAct: Synergizing reasoning and acting in language models. In The Eleventh International Conference on Learning Representations (ICLR).
  42. A Environment Details Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, et al. 2023. LLaMA: Open and efficient foundation language models. Computing Research Repository (CoRR), arXiv:2302.…

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/lin-2024-decision-oriented-dialogue-human-ai/