Conference proceeding
Tailoring with Targeted Precision: Edit-Based Agents for Open-Domain Procedure Customization
FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: ACL 2024, pp 15597-15611
01 Jan 2024
Abstract
How-to procedures, such as how to plant a garden, are now used by millions of users, but sometimes need customizing to meet a user's specific needs, e.g., planting a garden without pesticides. Our goal is to measure and improve an LLM's ability to perform such customization. Our approach is to test several simple multi-LLM-agent architectures for customization, as well as an end-to-end LLM, using a new evaluation set, called CUSTOMPLANS, of over 200 WikiHow procedures each with a customization need. We find that a simple architecture with two LLM agents used sequentially performs best, one that edits a generic how-to procedure and one that verifies its executability, significantly outperforming (10.5% absolute) an end-to-end prompted LLM. This suggests that LLMs can be configured reasonably effectively for procedure customization. This also suggests that multi-agent editing architectures may be worth exploring further for other customization applications (e.g. coding, creative writing) in the future.
Metrics
5 Record Views
Details
- Title
- Tailoring with Targeted Precision: Edit-Based Agents for Open-Domain Procedure Customization
- Creators
- Yash Kumar Lai - Stony Brook UniversityLi Zhang - University of PennsylvaniaFaeze Brahman - Allen InstituteBodhisattwa Prasad Majumder - Allen InstitutePeter Clark - Allen InstituteNiket Tandon - Allen Institute
- Contributors
- A Martins (Editor)Srikumar (Editor)L W Ku (Editor)
- Publication Details
- FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: ACL 2024, pp 15597-15611
- Publisher
- Association for Computational Linguistics
- Number of pages
- 15
- Resource Type
- Conference proceeding
- Language
- English
- Academic Unit
- Computer Science
- Web of Science ID
- WOS:001391786807018
- Other Identifier
- 991022123455304721
InCites Highlights
Data related to this publication, from InCites Benchmarking & Analytics tool:
- Collaboration types
- Domestic collaboration
- Web of Science research areas
- Computer Science, Artificial Intelligence
- Computer Science, Interdisciplinary Applications
- Computer Science, Theory & Methods