Is Preference Alignment Always the Best Option to Enhance LLM-Based Translation? An Empirical Analysis

• Main Authors: Gisserot-Boukhlef, Hippolyte, Rei, Ricardo, Malherbe, Emmanuel, Hudelot, Céline, Colombo, Pierre, Guerreiro, Nuno M
• Format: Journal Article
• Language: English
• Published: 30.09.2024
• Subjects: Computer Science - Computation and Language

Neural metrics for machine translation (MT) evaluation have become increasingly prominent due to their superior correlation with human judgments compared to traditional lexical metrics. Researchers have therefore utilized neural metrics through quality-informed decoding strategies, achieving better...