Language Models that Seek for Knowledge: Modular Search & Generation for Dialogue and Prompt Completion

Kurt Shuster, Mojtaba Komeili, Leonard Adolphs, Stephen Roller, Arthur Szlam, Jason Weston


Abstract
Language models (LMs) have recently been shown to generate more factual responses by employing modularity (Zhou et al., 2022) in combination with retrieval (Adolphs et al., 2021). We extend the recent approach of Adolphs et al. (2021) to include internet search as a module. Our SeeKeR (Search engine->Knowledge->Response) method thus applies a single LM to three modular tasks in succession: search, generating knowledge, and generating a final response. We show that, when using SeeKeR as a dialogue model, it outperforms the state-of-the-art model BlenderBot 2 (Chen et al., 2021) on open-domain knowledge-grounded conversations for the same number of parameters, in terms of consistency, knowledge and per-turn engagingness. SeeKeR applied to topical prompt completions as a standard language model outperforms GPT2 (Radford et al., 2019) and GPT3 (Brown et al., 2020) in terms of factuality and topicality, despite GPT3 being a vastly larger model. Our code and models are made publicly available.
Anthology ID:
2022.findings-emnlp.27
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2022
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
373–393
Language:
URL:
https://aclanthology.org/2022.findings-emnlp.27
DOI:
10.18653/v1/2022.findings-emnlp.27
Bibkey:
Cite (ACL):
Kurt Shuster, Mojtaba Komeili, Leonard Adolphs, Stephen Roller, Arthur Szlam, and Jason Weston. 2022. Language Models that Seek for Knowledge: Modular Search & Generation for Dialogue and Prompt Completion. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 373–393, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Language Models that Seek for Knowledge: Modular Search & Generation for Dialogue and Prompt Completion (Shuster et al., Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-emnlp.27.pdf