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

Domaine:

natural language processing

Type de record:

papersoftware

Créateur:

TraNguTraHoa

Hôte:

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: github.com. 18 pages

Visit

arxiv.org

Similaires

A Few‐Shot Learning Approach for a Multilingual Agro‐Information Question Answering SystemTa'keed: The First Generative Fact-Checking System for Arabic ClaimsAfrIFact: Cultural Information Retrieval, Evidence Extraction and Fact Checking for African LanguagesAnswering an Amharic Language Semantic Question over Interlinked DataAn ontology driven question answering system for fatawa retrievalDialogue based question answering system in Telugu

A Few‐Shot Learning Approach for a Multilingual Agro‐Information Question Answering System

ABSTRACT Across numerous households in Sub‐Saharan Africa, agriculture plays a crucial role. One so

Ta'keed: The First Generative Fact-Checking System for Arabic Claims

This paper introduces Ta'keed, an explainable Arabic automatic fact-checking system. While existing

AfrIFact: Cultural Information Retrieval, Evidence Extraction and Fact Checking for African Languages

Assessing the veracity of a claim made online is a complex and important task with real-world implications. When these claims are directed at communities with limited access to information and the content concerns issues such as healthcare and culture, the conseque

Answering an Amharic Language Semantic Question over Interlinked Data

An ontology driven question answering system for fatawa retrieval

This work aims to propose a system for the Algerian Fatawa House in orderto facilitate the task of t