Combining Discourse Coherence with Large Language Models for More Inclusive, Equitable, and Robust Task-Oriented Dialogue

Katherine Atwell, Mert Inan, Anthony B. Sicilia, Malihe Alikhani


Abstract
Large language models (LLMs) are capable of generating well-formed responses, but using LLMs to generate responses on the fly is not yet feasible for many task-oriented systems. Modular architectures are often still required for safety and privacy guarantees on the output. We hypothesize that an offline generation approach using discourse theories, formal grammar rules, and LLMs can allow us to generate human-like, coherent text in a more efficient, robust, and inclusive manner within a task-oriented setting. To this end, we present the first discourse-aware multimodal task-oriented dialogue system that combines discourse theories with offline LLM generation. We deploy our bot as an app to the general public and keep track of the user ratings for six months. Our user ratings show an improvement from 2.8 to 3.5 out of 5 with the introduction of discourse coherence theories. We also show that our model reduces misunderstandings in the dialect of African-American Vernacular English from 93% to 57%. While terms of use prevent us from releasing our entire codebase, we release our code in a format that can be integrated into most existing dialogue systems.
Anthology ID:
2024.lrec-main.314
Volume:
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
Month:
May
Year:
2024
Address:
Torino, Italia
Editors:
Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
Venues:
LREC | COLING
SIG:
Publisher:
ELRA and ICCL
Note:
Pages:
3538–3552
Language:
URL:
https://aclanthology.org/2024.lrec-main.314
DOI:
Bibkey:
Cite (ACL):
Katherine Atwell, Mert Inan, Anthony B. Sicilia, and Malihe Alikhani. 2024. Combining Discourse Coherence with Large Language Models for More Inclusive, Equitable, and Robust Task-Oriented Dialogue. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 3538–3552, Torino, Italia. ELRA and ICCL.
Cite (Informal):
Combining Discourse Coherence with Large Language Models for More Inclusive, Equitable, and Robust Task-Oriented Dialogue (Atwell et al., LREC-COLING 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.lrec-main.314.pdf