VLSP 2025 MLQA-TSR Challenge: Vietnamese Multimodal Legal Question Answering on Traffic Sign Regulation

TL;DR

This paper introduces the VLSP 2025 MLQA-TSR challenge, a Vietnamese multimodal legal question answering task focused on traffic sign regulation, providing a benchmark dataset and reporting state-of-the-art results.

Contribution

It presents a new multimodal legal question answering benchmark for Vietnamese traffic sign regulation and evaluates systems on retrieval and answering tasks.

Findings

F2 score of 64.55% for legal retrieval

86.30% accuracy for question answering

Benchmark dataset for Vietnamese multimodal legal domain

Abstract

This paper presents the VLSP 2025 MLQA-TSR - the multimodal legal question answering on traffic sign regulation shared task at VLSP 2025. VLSP 2025 MLQA-TSR comprises two subtasks: multimodal legal retrieval and multimodal question answering. The goal is to advance research on Vietnamese multimodal legal text processing and to provide a benchmark dataset for building and evaluating intelligent systems in multimodal legal domains, with a focus on traffic sign regulation in Vietnam. The best-reported results on VLSP 2025 MLQA-TSR are an F2 score of 64.55% for multimodal legal retrieval and an accuracy of 86.30% for multimodal question answering.