Abstract
Achieving consensus among diverse opinions through multi-round discussions can be a complex process. The advent of large language models (LLMs) offers promising avenues for resolving this challenge, given their prowess in understanding and analyzing human sentiments. However, existing approaches typically focus on single-round discussion, limiting their effectiveness in real-world discussion scenarios. In response to this, we proposes a two-layer facilitation agent modeled a multi-round discussion as a Markov decision process (MDP) to foster efficient agreement. The model comprises a high-level reinforcement learning-based agent, deciding the optimal facilitation action such as facilitation time and facilitation prompt. In the low-level, a large language model that generates the facilitation message based on the facilitation action. Our agent dynamically chooses facilitation moments, generates novel content, and directs the discussion towards consensus. Our methodology was validated across several different topic-based discussions, demonstrating excellent performance in achieving agreement swiftly across all.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bakker, M., et al.: Fine-tuning language models to find agreement among humans with diverse preferences. Adv. Neural. Inf. Process. Syst. 35, 38176–38189 (2022)
Brown, T., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877–1901 (2020)
Coulon, R., Judge, S.: An evolutionary algorithm for consensus building in inter-laboratory comparisons. Metrologia 58(6), 065007 (2021)
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)
Ding, R.X., et al.: Large-scale decision-making: Characterization, taxonomy, challenges and future directions from an artificial intelligence and applications perspective. Inform. Fusion 59, 84–102 (2020)
Ding, S., Ito, T.: Self-agreement: a framework for fine-tuning language models to find agreement among diverse opinions. arXiv preprint arXiv:2305.11460 (2023)
Du, Y., et al.: Guiding pretraining in reinforcement learning with large language models. arXiv preprint arXiv:2302.06692 (2023)
Leslie, D.: Tackling covid-19 through responsible ai innovation: five steps in the right direction. Harvard Data Sci. Rev. 10 (2020)
Min, B., et al.: Recent advances in natural language processing via large pre-trained language models: A survey. arXiv preprint arXiv:2111.01243 (2021)
Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529–533 (2015)
Raab, J., Susskind, L.: New approaches to consensus building and speeding up large-scale energy infrastructure projects (2022)
Radford, A., Narasimhan, K., Salimans, T., Sutskever, I., et al.: Improving language understanding by generative pre-training (2018)
Shin, J., Hedderich, M.A., Lucero, A., Oulasvirta, A.: Chatbots facilitating consensus-building in asynchronous co-design. In: Proceedings of the 35th Annual ACM Symposium on User Interface Software and Technology, pp. 1–13 (2022)
Vaswani, A., et al.: Attention is all you need. In: Advances in neural information processing systems 30 (2017)
Watkins, C.J., Dayan, P.: Q-learning. Mach. Learn. 8(3–4), 279–292 (1992)
Yang, C., Gu, W., Ito, T.: Toward case-based reasoning facilitation for online discussion in deliberation. In: 2019 IEEE 23rd International Conference on Computer Supported Cooperative Work in Design (CSCWD), pp. 517–523. IEEE (2019)
Acknowledgement
This work was supported by a CREST Grant (JPMJCR20D1) from Japan Science and Technology Agency (JST) and a Grant-in-Aid for Scientific Research (C) (23K11230) from the Japan Society for the Promotion of Science (JSPS).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Ding, S., Ito, T. (2024). A Deep Reinforcement Learning Based Facilitation Agent for Consensus Building Among Multi-Round Discussions. In: Liu, F., Sadanandan, A.A., Pham, D.N., Mursanto, P., Lukose, D. (eds) PRICAI 2023: Trends in Artificial Intelligence. PRICAI 2023. Lecture Notes in Computer Science(), vol 14327. Springer, Singapore. https://doi.org/10.1007/978-981-99-7025-4_23
Download citation
DOI: https://doi.org/10.1007/978-981-99-7025-4_23
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-7024-7
Online ISBN: 978-981-99-7025-4
eBook Packages: Computer ScienceComputer Science (R0)