DialGuide: Aligning Dialogue Model Behavior with Developer Guidelines

Prakhar Gupta, Yang Liu, Di Jin, Behnam Hedayatnia, Spandana Gella, Sijia Liu, Patrick Lange, Julia Hirschberg, Dilek Hakkani-Tur


Abstract
Dialogue models are able to generate coherent and fluent responses, but they can still be challenging to control and may produce non-engaging, unsafe results. This unpredictability diminishes user trust and can hinder the use of the models in the real world. To address this, we introduce DialGuide, a novel framework for controlling dialogue model behavior using natural language rules, or guidelines. These guidelines provide information about the context they are applicable to and what should be included in the response, allowing the models to generate responses that are more closely aligned with the developer’s expectations and intent. We evaluate DialGuide on three tasks in open-domain dialogue response generation: guideline selection, response generation, and response entailment verification. Our dataset contains 10,737 positive and 15,467 negative dialogue context-response-guideline triplets across two domains - chit-chat and safety. We provide baseline models for the tasks and benchmark their performance. We also demonstrate that DialGuide is effective in the dialogue safety domain, producing safe and engaging responses that follow developer guidelines.
Anthology ID:
2023.findings-emnlp.935
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2023
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
14031–14047
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.935
DOI:
10.18653/v1/2023.findings-emnlp.935
Bibkey:
Cite (ACL):
Prakhar Gupta, Yang Liu, Di Jin, Behnam Hedayatnia, Spandana Gella, Sijia Liu, Patrick Lange, Julia Hirschberg, and Dilek Hakkani-Tur. 2023. DialGuide: Aligning Dialogue Model Behavior with Developer Guidelines. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 14031–14047, Singapore. Association for Computational Linguistics.
Cite (Informal):
DialGuide: Aligning Dialogue Model Behavior with Developer Guidelines (Gupta et al., Findings 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/add_acl24_videos/2023.findings-emnlp.935.pdf