Zixiao Zhu


pdf bib
PromptExplainer: Explaining Language Models through Prompt-based Learning
Zijian Feng | Hanzhang Zhou | Zixiao Zhu | Kezhi Mao
Findings of the Association for Computational Linguistics: EACL 2024

Pretrained language models have become workhorses for various natural language processing (NLP) tasks, sparking a growing demand for enhanced interpretability and transparency. However, prevailing explanation methods, such as attention-based and gradient-based strategies, largely rely on linear approximations, potentially causing inaccuracies such as accentuating irrelevant input tokens. To mitigate the issue, we develop PromptExplainer, a novel method for explaining language models through prompt-based learning. PromptExplainer aligns the explanation process with the masked language modeling (MLM) task of pretrained language models and leverages the prompt-based learning framework for explanation generation. It disentangles token representations into the explainable embedding space using the MLM head and extracts discriminative features with a verbalizer to generate class-dependent explanations. Extensive experiments demonstrate that PromptExplainer significantly outperforms state-of-the-art explanation methods.

pdf bib
EDEntail: An Entailment-based Few-shot Text Classification with Extensional Definition
Zixiao Zhu | Junlang Qian | Zijian Feng | Hanzhang Zhou | Kezhi Mao
Findings of the Association for Computational Linguistics: NAACL 2024

Few-shot text classification has seen significant advancements, particularly with entailment-based methods, which typically use either class labels or intensional definitions of class labels in hypotheses for label semantics expression. In this paper, we propose EDEntail, a method that employs extensional definition (EDef) of class labels in hypotheses, aiming to express the semantics of class labels more explicitly. To achieve the above goal, we develop an algorithm to gather and select extensional descriptive words of class labels and then order and format them into a sequence to form hypotheses. Our method has been evaluated and compared with state-of-the-art models on five classification datasets. The results demonstrate that our approach surpasses the supervised-learning methods and prompt-based methods under the few-shot setting, which underlines the potential of using an extensional definition of class labels for entailment-based few-shot text classification. Our code is available at https://github.com/MidiyaZhu/EDEntail.