Reasoning-Oriented and Analogy-Based Methods for Locating and Editing in Zero-Shot Event-Relational Reasoning
This addresses computational and interpretability bottlenecks in natural language processing for researchers and practitioners working on event-relational reasoning.
The paper tackles the problem of computational inefficiency and lack of interpretability in zero-shot event-relational reasoning by proposing ROLE and ABLE methods for locating and editing language model modules. ROLE improves interpretability and reasoning performance with reduced computational cost, while ABLE achieves state-of-the-art results in zero-shot reasoning.
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.