用神经网络自动学习注意力模式转为关键词重要性，提升模型解释力。
Learning to Explain: Supervised Token Attribution from Transformer Attention Patterns
- 设计轻量网络ExpNet，从注意力模式直接映射词元重要性
- 跨任务实验中优于多种已有解释方法，尤其在复杂场景表现更优
- 适合需要高可信度解释的医疗、金融等关键领域
可解释人工智能（XAI）在医疗、法律、金融等高风险应用中日益重要，因模型透明度不足而影响信任与问责。尽管变压器模型的自注意力机制已被用于理解模型关注点，但现有方法依赖人工设定的聚合策略和固定归因规则，而模型无关方法（如LIME、SHAP）需大量输入扰动，计算成本高。本文提出解释网络（ExpNet），一种轻量级神经网络，能自动学习从变压器注意力模式到词元级重要性得分的显式映射。相比以往方法，ExpNet无需预设规则，可自主发现最优注意力特征组合。我们在具有挑战性的跨任务设置下评估ExpNet，对比了四类方法的广泛基准测试，涵盖模型无关方法与基于注意力的技术。
原文摘要 · Abstract (English)
Explainable AI (XAI) has become critical as transformer-based models are deployed in high-stakes applications including healthcare, legal systems, and financial services, where opacity hinders trust and accountability. Transformers self-attention mechanisms have proven valuable for model interpretability, with attention weights successfully used to understand model focus and behavior (Xu et al., 2015); (Wiegreffe and Pinter, 2019). However, existing attention-based explanation methods rely on manually defined aggregation strategies and fixed attribution rules (Abnar and Zuidema, 2020a); (Chefer et al., 2021), while model-agnostic approaches (LIME, SHAP) treat the model as a black box and incur significant computational costs through input perturbation. We introduce Explanation Network (ExpNet), a lightweight neural network that learns an explicit mapping from transformer attention patterns to token-level importance scores. Unlike prior methods, ExpNet discovers optimal attention feature combinations automatically rather than relying on predetermined rules. We evaluate ExpNet in a challenging cross-task setting and benchmark it against a broad spectrum of model-agnostic methods and attention-based techniques spanning four methodological families.
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。