Evaluating Large Language Models for Diacritic Restoration in Romanian Texts: A Comparative Study

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Nadas, Mihai, Diosan, Laura
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908668862136320
author Nadas, Mihai
Diosan, Laura
author_facet Nadas, Mihai
Diosan, Laura
contents Automatic diacritic restoration is crucial for text processing in languages with rich diacritical marks, such as Romanian. This study evaluates the performance of several large language models (LLMs) in restoring diacritics in Romanian texts. Using a comprehensive corpus, we tested models including OpenAI's GPT-3.5, GPT-4, GPT-4o, Google's Gemini 1.0 Pro, Meta's Llama 2 and Llama 3, MistralAI's Mixtral 8x7B Instruct, airoboros 70B, and OpenLLM-Ro's RoLlama 2 7B, under multiple prompt templates ranging from zero-shot to complex multi-shot instructions. Results show that models such as GPT-4o achieve high diacritic restoration accuracy, consistently surpassing a neutral echo baseline, while others, including Meta's Llama family, exhibit wider variability. These findings highlight the impact of model architecture, training data, and prompt design on diacritic restoration performance and outline promising directions for improving NLP tools for diacritic-rich languages.
format Preprint
id arxiv_https___arxiv_org_abs_2511_13182
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Evaluating Large Language Models for Diacritic Restoration in Romanian Texts: A Comparative Study
Nadas, Mihai
Diosan, Laura
Computation and Language
Automatic diacritic restoration is crucial for text processing in languages with rich diacritical marks, such as Romanian. This study evaluates the performance of several large language models (LLMs) in restoring diacritics in Romanian texts. Using a comprehensive corpus, we tested models including OpenAI's GPT-3.5, GPT-4, GPT-4o, Google's Gemini 1.0 Pro, Meta's Llama 2 and Llama 3, MistralAI's Mixtral 8x7B Instruct, airoboros 70B, and OpenLLM-Ro's RoLlama 2 7B, under multiple prompt templates ranging from zero-shot to complex multi-shot instructions. Results show that models such as GPT-4o achieve high diacritic restoration accuracy, consistently surpassing a neutral echo baseline, while others, including Meta's Llama family, exhibit wider variability. These findings highlight the impact of model architecture, training data, and prompt design on diacritic restoration performance and outline promising directions for improving NLP tools for diacritic-rich languages.
title Evaluating Large Language Models for Diacritic Restoration in Romanian Texts: A Comparative Study
topic Computation and Language
url https://arxiv.org/abs/2511.13182