解决大模型解释性难题，让预测理由更可信。
Boosting Explainability through Selective Rationalization in Pre-trained Language Models
- 拆分模型为生成器与预测器，缓解文本冗余问题
- 在多个数据集上验证，显著提升理由可读性与准确性
- 适合关注模型可解释性的研究人员和应用开发者
预训练语言模型（PLMs）在自然语言处理中的广泛应用引发了对其解释性的关注。选择性理性化是一种自解释框架，通过选取人类可理解的输入子集作为预测依据。然而，现有理性化方法应用于PLMs时会出现严重退化和失败，生成次优或无意义的理由，损害了理性化方法的信任度并限制其在PLMs上的应用。本文发现，PLMs生成句子中词元同质性是问题的主要原因。为此，我们提出一种名为PLMR的方法，将PLM拆分为生成器与预测器，在完成任务的同时提供可解释理由。生成器通过剪枝无关词元缓解同质性，预测器则利用完整文本信息标准化预测。在两个常用数据集上对多种PLMs进行实验，结果表明PLMR能有效应对将选择性理性化应用于PLMs的挑战。
原文摘要 · Abstract (English)
The widespread application of pre-trained language models (PLMs) in natural language processing (NLP) has led to increasing concerns about their explainability. Selective rationalization is a self-explanatory framework that selects human-intelligible input subsets as rationales for predictions. Recent studies have shown that applying existing rationalization frameworks to PLMs will result in severe degeneration and failure problems, producing sub-optimal or meaningless rationales. Such failures severely damage trust in rationalization methods and constrain the application of rationalization techniques on PLMs. In this paper, we find that the homogeneity of tokens in the sentences produced by PLMs is the primary contributor to these problems. To address these challenges, we propose a method named Pre-trained Language Model's Rationalization (PLMR), which splits PLMs into a generator and a predictor to deal with NLP tasks while providing interpretable rationales. The generator in PLMR also alleviates homogeneity by pruning irrelevant tokens, while the predictor uses full-text information to standardize predictions. Experiments conducted on two widely used datasets across multiple PLMs demonstrate the effectiveness of the proposed method PLMR in addressing the challenge of applying selective rationalization to PLMs. Codes: https://github.com/ylb777/PLMR.
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。