One Cannot Stand for Everyone! Leveraging Multiple User Simulators to train Task-oriented Dialogue Systems
Yajiao Liu, Xin Jiang, Yichun Yin, Yasheng Wang, Fei Mi, Qun Liu, Xiang Wan, Benyou Wang
2023Year
5Citations
7Top-tier citations
Abstract
User simulators are agents designed to imitate human users; recent advances have found that Task-oriented Dialogue (ToD) systems optimized toward a user simulator could better satisfy the need of human users. However, this might result in a sub-optimal ToD system if it is tailored to only one ad hoc user simulator, since human users can behave differently. In this paper, we propose a framework called MUST 1 to optimize ToD systems via leveraging Multiple User SimulaTors.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Cited by top-tier papers7
- Flipping the Dialogue: Training and Evaluating User Language ModelsTarek Naous, Philippe Laban, Wei Xu, Jennifer NevilleICLR 2026 · 56 citations
- Know You First and Be You Better: Modeling Human-Like User Simulators via Implicit ProfilesKuang Wang, Xianfei Li, Shenghao Yang, Li Zhou et al.ACL 2025 · 24 citations
- SEER: Facilitating Structured Reasoning and Explanation via Reinforcement LearningGuoxin Chen, Kexin Tang, Chao Yang, Fuying Ye et al.ACL 2024 · 5 citations
- Strength Lies in Differences! Improving Strategy Planning for Non-collaborative Dialogues via Diversified User SimulationTong Zhang, Chen Huang, Yang Deng, Hongru Liang et al.EMNLP 2024 · 1 citation
- Thinking Alignment of Scenario-Oriented User SimulationXiaoting Wu, Yi Huang, Chunyang Gao, Mengfei Guo et al.ACL 2026
Builds on3
- End-to-End Neural Pipeline for Goal-Oriented Dialogue Systems using GPT-2DongHoon Ham, Jeong-Gwan Lee, Youngsoo Jang, Kee-Eung KimACL 2020 · 167 citations
- Multi-Agent Task-Oriented Dialog Policy Learning with Role-Aware Reward DecompositionRyuichi Takanobu, Runze Liang, Minlie HuangACL 2020 · 47 citations
- Transferable Dialogue Systems and User SimulatorsBo-Hsiang Tseng, Yinpei Dai, Florian Kreyssig, Bill ByrneACL 2021
Related papers
- TOD-BERT: Pre-trained Natural Language Understanding for Task-Oriented DialogueChien-Sheng Wu, Steven C. H. Hoi, Richard Socher, Caiming XiongEMNLP 2020 · 210 citations
- Rethinking Task-Oriented Dialogue Systems: From Complex Modularity to Zero-Shot Autonomous AgentHeng-Da Xu, Xian-Ling Mao, Puhai Yang, Fanshu Sun et al.ACL 2024
- Learning Efficient Dialogue Policy from Demonstrations through ShapingHuimin Wang, Baolin Peng, Kam-Fai WongACL 2020 · 18 citations
- Amalgamating Knowledge from Two Teachers for Task-oriented Dialogue System with Adversarial TrainingWanwei He, Min Yang, Rui Yan, Chengming Li et al.EMNLP 2020 · 22 citations
- Non-Collaborative User Simulators for Tool AgentsJeonghoon Shim, Woojung Song, Cheyon Jin, Seungwon KooK et al.ICLR 2026 · 17 citations
