Reasoning-Oriented and Analogy-Based Methods for Locating and Editing in Zero-Shot Event-Relational Reasoning

Jingyao Tang, Lishuang Li, Liteng Mi, Haiming Wu, Hongbin Lu


Abstract
Zero-shot event-relational reasoning is an important task in natural language processing, and existing methods jointly learn a variety of event-relational prefixes and inference-form prefixes to achieve such tasks. However, training prefixes consumes large computational resources and lacks interpretability. Additionally, learning various relational and inferential knowledge inefficiently exploits the connections between tasks. Therefore, we first propose a method for Reasoning-Oriented Locating and Editing (ROLE), which locates and edits the key modules of the language model for reasoning about event relations, enhancing interpretability and also resource-efficiently optimizing the reasoning ability. Subsequently, we propose a method for Analogy-Based Locating and Editing (ABLE), which efficiently exploits the similarities and differences between tasks to optimize the zero-shot reasoning capability. Experimental results show that ROLE improves interpretability and reasoning performance with reduced computational cost. ABLE achieves SOTA results in zero-shot reasoning.
Anthology ID:
2025.coling-main.181
Volume:
Proceedings of the 31st International Conference on Computational Linguistics
Month:
January
Year:
2025
Address:
Abu Dhabi, UAE
Editors:
Owen Rambow, Leo Wanner, Marianna Apidianaki, Hend Al-Khalifa, Barbara Di Eugenio, Steven Schockaert
Venue:
COLING
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2645–2657
Language:
URL:
https://aclanthology.org/2025.coling-main.181/
DOI:
Bibkey:
Cite (ACL):
Jingyao Tang, Lishuang Li, Liteng Mi, Haiming Wu, and Hongbin Lu. 2025. Reasoning-Oriented and Analogy-Based Methods for Locating and Editing in Zero-Shot Event-Relational Reasoning. In Proceedings of the 31st International Conference on Computational Linguistics, pages 2645–2657, Abu Dhabi, UAE. Association for Computational Linguistics.
Cite (Informal):
Reasoning-Oriented and Analogy-Based Methods for Locating and Editing in Zero-Shot Event-Relational Reasoning (Tang et al., COLING 2025)
Copy Citation:
PDF:
https://aclanthology.org/2025.coling-main.181.pdf