PLEX:面向基于LLM的文本分类的无扰动局部解释
PLEX: Perturbation-free Local Explanations for LLM-Based Text Classification
AI总结:
针对LLM文本分类中LIME和SHAP等局部解释方法计算成本高的问题,提出无扰动局部解释方法PLEX,利用上下文嵌入和连体网络实现高效解释,在多项任务中与LIME和SHAP高度一致,并大幅降低时间和计算开销。
摘要:
大型语言模型(LLMs)在文本分类中表现出色,但其复杂性阻碍了可解释性,使得难以理解其预测背后的推理。诸如LIME和SHAP等可解释AI(XAI)方法通过识别有影响力的单词提供局部解释,但它们依赖于计算成本高昂的扰动。这些方法通常会生成数千个扰动句子并对每个句子进行推理,从而带来巨大的计算负担,尤其是在使用LLMs时。为了解决这一问题,我们提出了无扰动局部解释(PLEX),这是一种新颖的方法,利用从LLM中提取的上下文嵌入以及一个经过训练以与特征重要性分数对齐的“连体网络”风格的神经网络。这种一次性训练消除了后续扰动的需要,能够对任何新句子进行高效解释。我们在四个不同的分类任务(情感、假新闻、假COVID-19新闻和抑郁症)上展示了PLEX的有效性,显示其与LIME和SHAP的一致性超过92%。我们使用“压力测试”进行的评估表明,PLEX能准确识别有影响力的单词,当这些单词被移除时,会导致与LIME和SHAP观察到的分类准确率相似的下降。值得注意的是,在某些情况下,PLEX在捕获关键特征的影响方面表现出更优越的性能。PLEX显著加速了解释过程,分别将时间和计算开销降低了两个和四个数量级。这项工作为可解释的基于LLM的文本分类提供了一个有前景的解决方案。
英文摘要:
Large Language Models (LLMs) excel in text classification, but their complexity hinders interpretability, making it difficult to understand the reasoning behind their predictions. Explainable AI (XAI) methods like LIME and SHAP offer local explanations by identifying influential words, but they rely on computationally expensive perturbations. These methods typically generate thousands of perturbed sentences and perform inferences on each, incurring a substantial computational burden, especially with LLMs. To address this, we propose \underline{P}erturbation-free \underline{L}ocal \underline{Ex}planation (PLEX), a novel method that leverages the contextual embeddings extracted from the LLM and a ``Siamese network" style neural network trained to align with feature importance scores. This one-off training eliminates the need for subsequent perturbations, enabling efficient explanations for any new sentence. We demonstrate PLEX's effectiveness on four different classification tasks (sentiment, fake news, fake COVID-19 news and depression), showing more than 92\% agreement with LIME and SHAP. Our evaluation using a ``stress test" reveals that PLEX accurately identifies influential words, leading to a similar decline in classification accuracy as observed with LIME and SHAP when these words are removed. Notably, in some cases, PLEX demonstrates superior performance in capturing the impact of key features. PLEX dramatically accelerates explanation, reducing time and computational overhead by two and four orders of magnitude, respectively. This work offers a promising solution for explainable LLM-based text classification.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。