ACL Findings2023
Towards Zero-Shot Persona Dialogue Generation with In-Context Learning
Xinchao Xu, Zeyang Lei, Wenquan Wu, Zheng-Yu Niu, Hua Wu, Haifeng Wang
Abstract
Much work has been done to improve persona consistency by finetuning a pretrained dialogue model on high-quality human-annoated persona datasets. However, these methods still face the challenges of high cost and poor scalability. To this end, we propose a simpleyet-effective approach to significantly improve zero-shot persona consistency via in-context learning. Specifically, we first pre-train a persona-augmented dialogue generation model and then utilize in-context prompting mechanism to realize zero-shot persona customization. Experimental results demonstrate that our method can dramatically improve persona consistency without compromising coherence and informativeness in zero-shot settings.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
1 top-tier paper has cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- Personalized Generation In Large Model Era: A Survey cites BoB: BERT Over BERT for Training Persona-based Dialogue Models from Limited Personalized Data
- PLATO-2: Towards Building an Open-Domain Chatbot via Curriculum Learning cites Language Models are Few-Shot Learners
- BoB: BERT Over BERT for Training Persona-based Dialogue Models from Limited Personalized Data cites You Impress Me: Dialogue Generation via Mutual Persona Perception
- Long Time No See! Open-Domain Conversation with Long-Term Persona Memory cites PLATO-2: Towards Building an Open-Domain Chatbot via Curriculum Learning
Cited by top-tier papers1
Builds on6
- Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
- You Impress Me: Dialogue Generation via Mutual Persona PerceptionQian Liu, Yihong Chen, Bei Chen, Jian-Guang Lou et al.ACL 2020 · 144 citations
- PLATO-2: Towards Building an Open-Domain Chatbot via Curriculum LearningSiqi Bao, Huang He, Fan Wang, Hua Wu et al.ACL Findings 2021 · 94 citations
- Long Time No See! Open-Domain Conversation with Long-Term Persona MemoryXinchao Xu, Zhibin Gou, Wenquan Wu, Zheng-Yu Niu et al.ACL Findings 2022 · 65 citations
- BoB: BERT Over BERT for Training Persona-based Dialogue Models from Limited Personalized DataHaoyu Song, Yan Wang, Kaiyan Zhang, Wei-Nan Zhang et al.ACL 2021
Related papers
- Learning to Know Myself: A Coarse-to-Fine Persona-Aware Training Framework for Personalized Dialogue GenerationYunpeng Li, Yue Hu, Yajing Sun, Luxi Xing et al.AAAI 2023 · 9 citations
- PAED: Zero-Shot Persona Attribute Extraction in DialoguesLuyao Zhu, Wei Li, Rui Mao, Vlad Pandelea et al.ACL 2023 · 30 citations
- When Harry Meets Superman: The Role of The Interlocutor in Persona-Based Dialogue GenerationDaniela Occhipinti, Marco Guerini, Malvina NissimACL 2025 · 1 citation
- "In-Dialogues We Learn": Towards Personalized Dialogue Without Pre-defined Profiles through In-Dialogue LearningChuanqi Cheng, Quan Tu, Wei Wu, Shuo Shang et al.EMNLP 2024 · 3 citations
- A Disentangled-Attention Based Framework with Persona-Aware Prompt Learning for Dialogue GenerationPingsheng Liu, Zhengjie Huang, Xiechi Zhang, Linlin Wang et al.AAAI 2023 · 8 citations
