P5: Plug-and-Play Persona Prompting for Personalized Response Selection
This addresses the problem of personalized response selection for chatbot developers by offering a more flexible and data-efficient approach, though it appears incremental as it builds on existing prompting techniques.
The paper tackles the challenges of expensive persona-grounded data collection and inconsistent persona consideration in chatbots by proposing a plug-and-play persona prompting method, achieving improvements of up to 7.71 points in zero-shot settings and 3.39 points over previous state-of-the-art with fine-tuning.
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 and 1.04 points in the original persona and revised persona, respectively. The fine-tuned model improved the previous state-of-the-art system by 1.95 and 3.39 points in the original persona and revised persona, respectively. To the best of our knowledge, this is the first attempt to solve the problem of personalized response selection using prompt sequences. Our code is available on github~\footnote{https://github.com/rungjoo/plug-and-play-prompt-persona}.