提出两种新方法，让模型更高效、可解释地完成零样本事件关系推理。
Reasoning-Oriented and Analogy-Based Methods for Locating and Editing in Zero-Shot Event-Relational Reasoning
- 通过定位与编辑语言模型关键模块，实现推理过程的可解释优化。
- 在零样本场景下，性能达到当前最优，计算开销显著降低。
- 适合关注模型可解释性与高效推理的研究者和开发者。
零样本事件关系推理是自然语言处理中的重要任务，现有方法需联合学习多种事件关系前缀与推理形式前缀，但训练前缀消耗大量计算资源且缺乏可解释性。同时，各类关系与推理知识的学习效率低，未能有效利用任务间的关联。为此，我们提出面向推理的定位与编辑方法（ROLE），通过定位并编辑语言模型中用于事件关系推理的关键模块，提升可解释性，并以更低资源成本优化推理能力。随后，提出基于类比的定位与编辑方法（ABLE），通过挖掘任务间的相似性与差异性，高效优化零样本推理能力。实验表明，ROLE提升了可解释性与推理性能，同时降低计算开销；ABLE在零样本推理任务上取得当前最优结果。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。