LLMs Learn Task Heuristics from Demonstrations: A Heuristic-Driven Prompting Strategy for Document-Level Event Argument Extraction

Hanzhang Zhou, Junlang Qian, Zijian Feng, Lu Hui, Zixiao Zhu, Kezhi Mao


Abstract
In this study, we explore in-context learning (ICL) in document-level event argument extraction (EAE) to alleviate the dependency on large-scale labeled data for this task. We introduce the Heuristic-Driven Link-of-Analogy (HD-LoA) prompting tailored for the EAE task. Specifically, we hypothesize and validate that LLMs learn task-specific heuristics from demonstrations in ICL. Building upon this hypothesis, we introduce an explicit heuristic-driven demonstration construction approach, which transforms the haphazard example selection process into a systematic method that emphasizes task heuristics. Additionally, inspired by the analogical reasoning of human, we propose the link-of-analogy prompting, which enables LLMs to process new situations by drawing analogies to known situations, enhancing their performance on unseen classes beyond limited ICL examples. Experiments show that our method outperforms existing prompting methods and few-shot supervised learning methods on document-level EAE datasets. Additionally, the HD-LoA prompting shows effectiveness in other tasks like sentiment analysis and natural language inference, demonstrating its broad adaptability.
Anthology ID:
2024.acl-long.647
Volume:
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
11972–11990
Language:
URL:
https://aclanthology.org/2024.acl-long.647
DOI:
10.18653/v1/2024.acl-long.647
Bibkey:
Cite (ACL):
Hanzhang Zhou, Junlang Qian, Zijian Feng, Lu Hui, Zixiao Zhu, and Kezhi Mao. 2024. LLMs Learn Task Heuristics from Demonstrations: A Heuristic-Driven Prompting Strategy for Document-Level Event Argument Extraction. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 11972–11990, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
LLMs Learn Task Heuristics from Demonstrations: A Heuristic-Driven Prompting Strategy for Document-Level Event Argument Extraction (Zhou et al., ACL 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-2024-clasp/2024.acl-long.647.pdf