SemViQA: A Semantic Question Answering System for Vietnamese Information Fact-Checking

2025-03-02

AI Summary

To address the accuracy bottleneck in low-resource Vietnamese fact-checking—caused by semantic ambiguity, homophonic heteronymy, and complex syntax—this paper proposes a synergistic framework comprising Semantic-driven Evidence Retrieval (SER) and Two-stage Verdict Classification (TVC). Key innovations include a Vietnamese-specific pretrained encoder, hierarchical semantic similarity matching, and a dual-granularity interpretable classification mechanism. We further introduce SemViQA Faster, a lightweight model achieving state-of-the-art (SOTA) accuracy with 7× inference acceleration. Evaluated on ISE-DSC01 and ViWikiFC, SemViQA Faster attains strict accuracies of 78.97% and 80.82%, respectively—substantially outperforming existing methods. The framework secured first place in the UIT Data Science Challenge and establishes a new benchmark for Vietnamese fact-checking.

Technology Category

• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)
• Computer Vision: Image and Video Retrieval
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

The rise of misinformation, exacerbated by Large Language Models (LLMs) like GPT and Gemini, demands robust fact-checking solutions, especially for low-resource languages like Vietnamese. Existing methods struggle with semantic ambiguity, homonyms, and complex linguistic structures, often trading accuracy for efficiency. We introduce SemViQA, a novel Vietnamese fact-checking framework integrating Semantic-based Evidence Retrieval (SER) and Two-step Verdict Classification (TVC). Our approach balances precision and speed, achieving state-of-the-art results with 78.97% strict accuracy on ISE-DSC01 and 80.82% on ViWikiFC, securing 1st place in the UIT Data Science Challenge. Additionally, SemViQA Faster improves inference speed 7x while maintaining competitive accuracy. SemViQA sets a new benchmark for Vietnamese fact verification, advancing the fight against misinformation. The source code is available at: https://github.com/DAVID-NGUYEN-S16/SemViQA.

Problem

• Addresses misinformation in Vietnamese using fact-checking
• Tackles semantic ambiguity and complex linguistic structures
• Improves accuracy and speed for low-resource language processing

Innovation

• Semantic-based Evidence Retrieval for Vietnamese
• Two-step Verdict Classification system
• Balances accuracy with inference speed