Interpreting User Requests in the Context of Natural Language Standing Instructions

Nikita Moghe, Patrick Xia, Jacob Andreas, Jason Eisner, Benjamin Van Durme, Harsh Jhamtani


Abstract
Users of natural language interfaces, frequently powered by Large Language Models (LLMs), must often repeat their full set of preferences each time they make a similar request. We describe an approach to LLM-based dialogue modeling in which persistent user constraints and preferences – collectively termed standing instructions – are provided as additional context for such interfaces. For example, when a user states “I’m hungry”, a previously expressed preference for Persian food can be automatically added to the LLM prompt, influencing the search for relevant restaurants.We develop NLSI, a language-to-program dataset consisting of over 2.4K English dialogues spanning 17 domains, in which each dialogue is paired with a user profile (a set of user-specific standing instructions) and corresponding structured representations (a sequence of API calls). A key challenge in NLSI is to identify which subset of the standing instructions is applicable to a given dialogue. NLSI contains diverse phenomena, from simple preferences to interdependent instructions such as triggering a hotel search whenever the user is booking tickets to an event. We conduct experiments on NLSI using prompting with large language models and various retrieval approaches, achieving a maximum of 46% exact match on API prediction. Our results demonstrate the challenges in identifying the relevant standing instructions and their interpretation into API calls
Anthology ID:
2024.findings-naacl.255
Volume:
Findings of the Association for Computational Linguistics: NAACL 2024
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Kevin Duh, Helena Gomez, Steven Bethard
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4043–4060
Language:
URL:
https://aclanthology.org/2024.findings-naacl.255
DOI:
10.18653/v1/2024.findings-naacl.255
Bibkey:
Cite (ACL):
Nikita Moghe, Patrick Xia, Jacob Andreas, Jason Eisner, Benjamin Van Durme, and Harsh Jhamtani. 2024. Interpreting User Requests in the Context of Natural Language Standing Instructions. In Findings of the Association for Computational Linguistics: NAACL 2024, pages 4043–4060, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
Interpreting User Requests in the Context of Natural Language Standing Instructions (Moghe et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-naacl.255.pdf