Logo image
Tailoring with Targeted Precision: Edit-Based Agents for Open-Domain Procedure Customization
Conference proceeding   Open access

Tailoring with Targeted Precision: Edit-Based Agents for Open-Domain Procedure Customization

Yash Kumar Lai, Li Zhang, Faeze Brahman, Bodhisattwa Prasad Majumder, Peter Clark and Niket Tandon
FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: ACL 2024, pp 15597-15611
01 Jan 2024
url
https://doi.org/10.18653/v1/2024.findings-acl.921View
Published, Version of Record (VoR) Open

Abstract

Computer Science, Artificial Intelligence Computer Science, Interdisciplinary Applications Computer Science, Theory & Methods Science & Technology Computer Science Technology
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

Details

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
Logo image