A rationale-guided knowledge distillation framework for cross-lingual stance detection using Chain-of-Thought prompting to guide Large Language Models in generating informative rationales, and distill the resulting reasoning knowledge into a compact student model.
Abstract
Stance detection aims to identify whether a text expresses a favorable or opposing attitude toward a given target, and serves as an important task for various downstream applications. Although existing studies have achieved strong performance in monolingual settings, especially in English, many low-resource languages such as Catalan still lack sufficient annotated data for training effective models. Cross-lingual stance detection alleviates this problem by transferring stance knowledge from resource-rich languages to low-resource languages. However, most existing methods mainly rely on semantic alignment between texts and targets, while ignoring the reasoning process required for reliable stance inference. Although Large Language Models provide strong reasoning ability, their high computational cost and inference latency limit practical deployment. To address these limitations, we propose a rationale-guided knowledge distillation framework for cross-lingual stance detection. Specifically, we use Chain-of-Thought prompting to guide Large Language Models in generating informative rationales, and distill the resulting reasoning knowledge into a compact student model. We further design a dual-path distillation mechanism to align rationale-enhanced and rationale-free representations, together with their prediction distributions. In addition, two contrastive learning strategies are introduced to improve stance discrimination. Experiments on multilingual benchmarks demonstrate that our method consistently outperforms competitive baselines.
A framework for stance detection in Manipuri editorial articles is proposed and the model reduces confusion between FOR and NEUTRAL editorials, which is one of the most critical problems for stance identification.
This paper introduces diagnostic word-ablation metrics to quantify this phenomenon and proposes a data-centric solution that can alleviate the observed overcorrection in stance-aware argument retrieval and demonstrates that, for sufficiently powerful models, this approach can alleviate the observed overcorrection.
Angelo Sparacino, Francesca Toni, Adam Dejl· 0 citations
We propose a modular, retrieval-augmented pipeline for computational argumentation that integrates two complementary components: ArgStance, a multi-task model for argument and stance reasoning, and TargetMatch, a contrastive retrieval model that treats target identification as a first-class retrieval task. We further formulate stance detection as a framing-aware problem, recognizing that the polarity of a stance toward a target depends on how the proposition is framed. To support broad generalization, we construct a large dataset spanning Kialo discussions, Wikipedia, and curated news articles, and introduce a cross-source injection strategy that mitigates domain and style biases. Our compact models achieve F1 scores of 0.94 for argument detection (ModernBERT-base) and 0.84 for same-side stance detection (ModernBERT-large), while TargetMatch attains a top-10 retrieval accuracy of 0.75. Under controlled zero-shot comparisons with large language models, our models remain competitive while offering advantages in reproducibility, deployment cost, and controllable intermediate predictions.
Antonis Charalampous, Constantinos Djouvas· Machine Learning and Knowled...· 0 citations
It is suggested that cross-lingual inconsistency is at least partly a selection problem, and that simple contextual interventions may outperform more invasive methods for robust, transferable alignment.
Lite-CoNER is proposed, a lightweight NER framework that achieves an effective balance between recognition accuracy and inference efficiency and provides a transparent view of the decision-making process, proving that lightweight models can effectively inherit complex logic through structured distillation.
Yang Wang, Lushuang Gao· International Conference on...· 0 citations
Knowledge-intensive multi-hop question answering requires systems to select evidence and compose dependent facts, yet multilingual benchmarks usually translate an entire example into one language. This hides failures at language boundaries inside the reasoning chain. We introduce XHotpotQA, a controlled benchmark for cross-lingual knowledge composition over mixed-language evidence. Each instance is modeled as an evidence-dependency graph whose question, bridge evidence, answer-bearing evidence, and distractors have explicit language assignments. The audited resource contains 15,661 training and 7,405 validation instances, with sentence-level support supervision and supplied distractors. In validation, 99.81% of items cross the question-to-gold-evidence language interface and 95.60% use gold paragraphs in different languages. Across three reader artifacts, full question-evidence mismatch is associated with 10.25 to 15.79 lower Unicode-aware answer F1 than partial alignment, and different-script evidence with deficits of 11.98 to 23.70 points; the corresponding adapted-selector contrasts are 1.71 and 1.78 points. Under this supplied-candidate design, the evaluated readers therefore show substantially larger condition-associated deficits than the selector. XHotpotQA provides role-aware diagnostics, modular evaluation, and an audited test bed for knowledge-based systems that must integrate evidence across languages.
Iman Barati, A. Ghafouri, B. Minaei-Bidgoli· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
