# Towards Transparent Stance Detection: A Zero-Shot Approach Using Implicit and Explicit Interpretability

arXiv: https://arxiv.org/abs/2511.03635 · HTML: https://mlsanity.com/paper/2511.03635/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 36 references that are in the map.
- First posted on arXiv 5 Nov 2025.

## Builds on (most cited first, 16 of 16)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [ERASER: A Benchmark to Evaluate Rationalized NLP Models](https://mlsanity.com/paper/1911.03429/) (2019)
- [NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models](https://mlsanity.com/paper/2405.17428/) (2024)
- [FinTextQA: A Dataset for Long-form Financial Question Answering](https://mlsanity.com/paper/2405.09980/) (2024)
- [Stance Detection with Collaborative Role-Infused LLM-Based Agents](https://mlsanity.com/paper/2310.10467/) (2023)
- [Stance Detection Benchmark: How Robust Is Your Stance Detection?](https://mlsanity.com/paper/2001.01565/) (2020)
- [Cross-Domain Label-Adaptive Stance Detection](https://mlsanity.com/paper/2104.07467/) (2021)
- [Stance Reasoner: Zero-Shot Stance Detection on Social Media with Explicit Reasoning](https://mlsanity.com/paper/2403.14895/) (2024)
- [Ladder-of-Thought: Using Knowledge as Steps to Elevate Stance Detection](https://mlsanity.com/paper/2308.16763/) (2023)
- [Collaborative Knowledge Infusion for Low-resource Stance Detection](https://mlsanity.com/paper/2403.19219/) (2024)
- [EDDA: A Encoder-Decoder Data Augmentation Framework for Zero-Shot Stance Detection](https://mlsanity.com/paper/2403.15715/) (2024)
- [Overriding Safety protections of Open-source Models](https://mlsanity.com/paper/2409.19476/) (2024)
- [Diagnosing Hate Speech Classification: Where Do Humans and Machines Disagree, and Why?](https://mlsanity.com/paper/2410.10153/) (2024)

## Abstract (arXiv)

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.