针对越南语虚假信息，提出高效精准的问答式核查系统。
SemViQA: A Semantic Question Answering System for Vietnamese Information Fact-Checking
- 结合语义检索与两步判断，提升越南语事实核查精度。
- 在两个数据集上分别达78.97%和80.82%严格准确率，排名第一。
- 推理速度提升7倍，适合实际部署场景使用。
misinformation 的泛滥，尤其是受 GPT、Gemini 等大语言模型推动，亟需高效的事实核查方案，尤其针对低资源语言如越南语。现有方法常因语义歧义、同音词及复杂句法结构而难以兼顾准确率与效率。本文提出 SemViQA，一个融合语义证据检索（SER）与两步判决分类（TVC）的越南语事实核查框架。该方法在 ISE-DSC01 数据集上实现 78.97% 的严格准确率，在 ViWikiFC 上达 80.82%，并获 UIT 数据科学挑战赛第一名。此外，SemViQA Faster 在保持竞争力准确率的前提下，将推理速度提升 7 倍。本工作为越南语事实核查设立了新基准，助力对抗虚假信息传播。代码已开源：https://github.com/DAVID-NGUYEN-S16/SemViQA。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。