Active Listening: Personalized Question Generation in Open-Domain Social Conversation with User Model Based Prompting

Kevin Bowden, Yue Fan, Winson Chen, Wen Cui, Davan Harrison, Xin Wang, Marilyn Walker


Abstract
Large language models (LLMs) capable of casual conversation have recently become widely available. We hypothesize that users of conversational systems want a more personalized experience, and existing work shows that users are highly receptive to personalized questions (PQs). Question Generation tasks, however, focus on factual questions from textual excerpts. To create a PQ generator, we first identify over 400 real user interests by anonymously aggregating ~39K user models. We then populate prompt templates with these 400 interests and use an LLM to generate PQs customized to user interests. The result is PerQs, a novel corpus of ~19K question/answer pairs. We evaluate PerQs at scale in the unique context of the Alexa Prize. Our results show significant positive effects on perceived conversation quality. We then fine-tune, deploy, and evaluate PerQy, a neural model that generates PQs in real-time. When evaluated against several competitive LLM baselines, PerQy produced the most natural and engaging responses.
Anthology ID:
2024.findings-emnlp.826
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2024
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
14120–14157
Language:
URL:
https://aclanthology.org/2024.findings-emnlp.826
DOI:
Bibkey:
Cite (ACL):
Kevin Bowden, Yue Fan, Winson Chen, Wen Cui, Davan Harrison, Xin Wang, and Marilyn Walker. 2024. Active Listening: Personalized Question Generation in Open-Domain Social Conversation with User Model Based Prompting. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 14120–14157, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Active Listening: Personalized Question Generation in Open-Domain Social Conversation with User Model Based Prompting (Bowden et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-emnlp.826.pdf