标题： 面向推理和类比的零样本事件关系推理中的定位与编辑方法 显示英文标题

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

摘要： 零样本事件关系推理是自然语言处理中的重要任务，现有方法联合学习多种事件关系前缀和推理形式前缀以完成此类任务。 然而，训练前缀消耗大量计算资源且缺乏可解释性。 此外，学习各种关系和推理知识低效地利用了任务之间的联系。 因此，我们首先提出一种面向推理的定位与编辑方法（ROLE），该方法定位并编辑语言模型中用于事件关系推理的关键模块，增强了可解释性，并且高效地优化了推理能力。 随后，我们提出一种基于类比的定位与编辑方法（ABLE），该方法高效利用任务之间的相似性和差异性以优化零样本推理能力。 实验结果表明，ROLE在降低计算成本的同时提高了可解释性和推理性能。 ABLE在零样本推理中达到了最先进结果。 显示英文摘要

摘要： 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.