ViMultiChoice: Toward a Method That Gives Explanation for Multiple-Choice Reading Comprehension in Vietnamese

2026-02-10

AI Summary

This study addresses the lack of interpretability in existing Vietnamese multiple-choice reading comprehension models. To this end, the authors construct a novel dataset that supports natural language explanation generation and propose ViMultiChoice, a method that jointly models answer selection and explanation generation for the first time in the Vietnamese context. ViMultiChoice employs an end-to-end architecture that integrates multi-choice discrimination with text generation techniques, specifically adapted to the linguistic characteristics of Vietnamese. Experimental results demonstrate that ViMultiChoice achieves state-of-the-art performance on both the ViMMRC 2.0 benchmark and the newly introduced dataset, significantly improving both accuracy and model interpretability.

Technology Category

• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models
• Computer Vision: Interpretability, Explainability, and Transparency
• Machine Learning: Transparent, Interpretable, Explainable ML

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Multiple-choice Reading Comprehension (MCRC) models aim to select the correct answer from a set of candidate options for a given question. However, they typically lack the ability to explain the reasoning behind their choices. In this paper, we introduce a novel Vietnamese dataset designed to train and evaluate MCRC models with explanation generation capabilities. Furthermore, we propose ViMultiChoice, a new method specifically designed for modeling Vietnamese reading comprehension that jointly predicts the correct answer and generates a corresponding explanation. Experimental results demonstrate that ViMultiChoice outperforms existing MCRC baselines, achieving state-of-the-art (SotA) performance on both the ViMMRC 2.0 benchmark and the newly introduced dataset. Additionally, we show that jointly training option decision and explanation generation leads to significant improvements in multiple-choice accuracy.

Problem

• Multiple-Choice Reading Comprehension
• Explanation Generation
• Vietnamese NLP
• Interpretability
• MCRC

Innovation

• explanation generation
• joint modeling
• Vietnamese reading comprehension
• multiple-choice QA
• ViMultiChoice