Towards Transparent Stance Detection: A Zero-Shot Approach Using Implicit and Explicit Interpretability
Zero-Shot Stance Detection (ZSSD) identifies the attitude of the post toward unseen targets. Existing research using contrastive, meta-learning, or data augmentation suffers from generalizability issues or lack of coherence between text and target. Recent works leveraging large language models (LLMs) for ZSSD focus either on improving unseen target-specific knowledge or generating explanations for stance analysis. However, most of these works are limited by their over-reliance on explicit reasoning, provide coarse explanations that lack nuance, and do not explicitly model the reasoning process, making it difficult to interpret the model's predictions. To address these issues, in our study, we develop a novel interpretable ZSSD framework, IRIS. We provide an interpretable understanding of the attitude of the input towards the target implicitly based on sequences within the text (implicit rationales) and explicitly based on linguistic measures (explicit rationales). IRIS considers stance detection as an information retrieval ranking task, understanding the relevance of implicit rationales for different stances to guide the model towards correct predictions without requiring the ground-truth of rationales, thus providing inherent interpretability. In addition, explicit rationales based on communicative features help decode the emotional and cognitive dimensions of stance, offering an interpretable understanding of the author's attitude towards the given target. Extensive experiments on the benchmark datasets of VAST, EZ-STANCE, P-Stance, and RFD using 50%, 30%, and even 10% training data prove the generalizability of our model, benefiting from the proposed architecture and interpretable design.
Code (0)
등록된 구현이 없습니다.
Tasks
Information RetrievalData AugmentationStance DetectionSimilar Papers 제목 키워드 기반
Zero-Shot Stance Detection: A Dataset and Model using Generalized Topic Representations
Stance detection is an important component of understanding hidden influences in everyday life. Since there are thousands of potential topics to take a stance on, most with little to no training data, we focus on zero-sh…
Stance DetectionZero-Shot Stance DetectionExploiting Sentiment and Common Sense for Zero-shot Stance Detection
The stance detection task aims to classify the stance toward given documents and topics. Since the topics can be implicit in documents and unseen in training data for zero-shot settings, we propose to boost the transfera…
Common Sense ReasoningStance DetectionZero-Shot Stance DetectionZero-shot Tweet-Level Stance Detection Enhanced by External Knowledge and Reflective Chain-of-Thought Reasoning
Zero-shot tweet-level stance detection confronts two primary challenges: (1) mitigating the context sparsity inherent in short texts, and (2) establishing the relevance between implicit targets and textual content. While…
Contrastive LearningData AugmentationKnowledge GraphsStance DetectionAdversarial Learning for Zero-Shot Stance Detection on Social Media
Stance detection on social media can help to identify and understand slanted news or commentary in everyday life. In this work, we propose a new model for zero-shot stance detection on Twitter that uses adversarial learn…
Stance DetectionZero-Shot Stance DetectionZero-Shot Detection of LLM-Generated Text via Implicit Reward Model
Large language models (LLMs) have demonstrated remarkable capabilities across various tasks. However, their ability to generate human-like text has raised concerns about potential misuse. This underscores the need for re…
Text Detection