paper-with-me

홈 › Papers

Do LLMs Understand Romanian Driving Laws? A Study on Multimodal and Fine-Tuned Question Answering

2025-09-28 · Eduard Barbu, Adrian Marius Dumitran arxiv

Ensuring that both new and experienced drivers master current traffic rules is critical to road safety. This paper evaluates Large Language Models (LLMs) on Romanian driving-law QA with explanation generation. We release a 1{,}208-question dataset (387 multimodal) and compare text-only and multimodal SOTA systems, then measure the impact of domain-specific fine-tuning for Llama 3.1-8B-Instruct and RoLlama 3.1-8B-Instruct. SOTA models perform well, but fine-tuned 8B models are competitive. Textual descriptions of images outperform direct visual input. Finally, an LLM-as-a-Judge assesses explanation quality, revealing self-preference bias. The study informs explainable QA for less-resourced languages.

📄 PDF Abstract BibTeX arXiv:2509.23715

Code (0)

등록된 구현이 없습니다.

Tasks

Explanation GenerationQuestion Answering

Similar Papers 제목 키워드 기반

RoD-TAL: A Benchmark for Answering Questions in Romanian Driving License Exams

2025-07-25 · Andrei Vlad Man, Răzvan-Alexandru Smădu, Cristian-George Craciun, Dumitru-Clementin Cercel 외 arxiv

The intersection of AI and legal systems presents a growing need for tools that support legal education, particularly in under-resourced languages such as Romanian. In this work, we aim to evaluate the capabilities of La…

Information RetrievalQuestion Answering

GRILE: A Benchmark for Grammar Reasoning and Explanation in Romanian LLMs

2025-08-19 · Adrian-Marius Dumitran, Alexandra-Mihaela Danila, Angela-Liliana Dumitran arxiv

LLMs (Large language models) have revolutionized NLP (Natural Language Processing), yet their pedagogical value for low-resource languages remains unclear. We present GRILE (Grammar Romanian Inference and Language Explan…

Explanation Generation

Hybrid Reasoning Based on Large Language Models for Autonomous Car Driving

2024-02-21 · Mehdi Azarafza, Mojtaba Nayyeri, Charles Steinmetz, Steffen Staab 외

Large Language Models (LLMs) have garnered significant attention for their ability to understand text and images, generate human-like text, and perform complex reasoning tasks. However, their ability to generalize this a…

Autonomous DrivingAutonomous VehiclesCommon Sense ReasoningDecision Making

RoBiologyDataChoiceQA: A Romanian Dataset for improving Biology understanding of Large Language Models

2025-09-30 · Dragos-Dumitru Ghinea, Adela-Nicoleta Corbeanu, Adrian-Marius Dumitran arxiv

In recent years, large language models (LLMs) have demonstrated significant potential across various natural language processing (NLP) tasks. However, their performance in domain-specific applications and non-English lan…

Prompt Engineering

Parameter Efficient Multimodal Instruction Tuning for Romanian Vision Language Models

2025-12-16 · George-Andrei Dima, Răzvan-Alexandru Smădu, Dumitru-Clementin Cercel arxiv

Focusing on low-resource languages is an essential step toward democratizing generative AI. In this work, we contribute to reducing the multimodal NLP resource gap for Romanian. We translate the widely known Flickr30K da…

Visual Question Answering