P5: Plug-and-Play Persona Prompting for Personalized Response Selection
Joosung Lee, Minsik Oh, Donghun Lee

TL;DR
This paper introduces a plug-and-play persona prompting method for chatbots that enhances personalized response selection, performs well in zero-shot settings, and reduces the need for expensive persona-grounded data.
Contribution
It presents the first prompt-based approach for personalized response selection, enabling zero-shot and fine-tuned improvements without extensive persona-grounded training data.
Findings
Zero-shot model improved persona response scores by 7.71 and 1.04 points.
Fine-tuned model outperformed previous state-of-the-art by 1.95 and 3.39 points.
Method reduces dependence on costly persona-grounded corpora.
Abstract
The use of persona-grounded retrieval-based chatbots is crucial for personalized conversations, but there are several challenges that need to be addressed. 1) In general, collecting persona-grounded corpus is very expensive. 2) The chatbot system does not always respond in consideration of persona at real applications. To address these challenges, we propose a plug-and-play persona prompting method. Our system can function as a standard open-domain chatbot if persona information is not available. We demonstrate that this approach performs well in the zero-shot setting, which reduces the dependence on persona-ground training data. This makes it easier to expand the system to other languages without the need to build a persona-grounded corpus. Additionally, our model can be fine-tuned for even better performance. In our experiments, the zero-shot model improved the standard model by 7.71…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsTopic Modeling · AI in Service Interactions · Speech and dialogue systems
