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

Yash Kumar Lal, Li Zhang, Faeze Brahman, Bodhisattwa Prasad Majumder, Peter Clark, Niket Tandon


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.
Anthology ID:
2024.findings-acl.921
Volume:
Findings of the Association for Computational Linguistics: ACL 2024
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
15597–15611
Language:
URL:
https://aclanthology.org/2024.findings-acl.921
DOI:
10.18653/v1/2024.findings-acl.921
Bibkey:
Cite (ACL):
Yash Kumar Lal, Li Zhang, Faeze Brahman, Bodhisattwa Prasad Majumder, Peter Clark, and Niket Tandon. 2024. Tailoring with Targeted Precision: Edit-Based Agents for Open-Domain Procedure Customization. In Findings of the Association for Computational Linguistics: ACL 2024, pages 15597–15611, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Tailoring with Targeted Precision: Edit-Based Agents for Open-Domain Procedure Customization (Lal et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-acl.921.pdf