对比三种解释方法，找出大模型决策背后的可靠线索。
Applied Explainability for Large Language Models: A Comparative Study
- 用梯度、注意力和模型无关法分析情感分类模型
- 梯度法解释最稳定，注意力法快但不准，模型无关法灵活但耗时
- 适合关心模型可信性与调试的NLP工程师
大语言模型在多项自然语言处理任务中表现优异，但其决策过程难以解释。这种不透明性影响了模型在实际系统中的信任度、调试与部署。本文对三种解释技术——Integrated Gradients、Attention Rollout 和 SHAP——在微调后的 DistilBERT 模型上进行应用比较，针对 SST-2 情感分类任务展开。研究不提出新方法，而是聚焦于在一致可复现设置下，现有方法的实际行为表现。结果表明：基于梯度的归因方法提供更稳定且直观的解释；基于注意力的方法计算效率高但与预测相关特征对齐较差；模型无关方法虽具灵活性，却带来更高计算成本与结果变异性。该研究揭示了各类解释方法之间的关键权衡，并强调其作为诊断工具而非确定性解释的作用。研究结果为从事基于Transformer的NLP系统的研究者与工程师提供了实用参考。本论文为预印本，尚未经过同行评审。
原文摘要 · Abstract (English)
Large language models (LLMs) achieve strong performance across many natural language processing tasks, yet their decision processes remain difficult to interpret. This lack of transparency creates challenges for trust, debugging, and deployment in real-world systems. This paper presents an applied comparative study of three explainability techniques: Integrated Gradients, Attention Rollout, and SHAP, on a fine-tuned DistilBERT model for SST-2 sentiment classification. Rather than proposing new methods, the focus is on evaluating the practical behavior of existing approaches under a consistent and reproducible setup. The results show that gradient-based attribution provides more stable and intuitive explanations, while attention-based methods are computationally efficient but less aligned with prediction-relevant features. Model-agnostic approaches offer flexibility but introduce higher computational cost and variability. This work highlights key trade-offs between explainability methods and emphasizes their role as diagnostic tools rather than definitive explanations. The findings provide practical insights for researchers and engineers working with transformer-based NLP systems. This is a preprint and has not undergone peer review.
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。