English

Reference-free Evaluation Metrics for Text Generation: A Survey

Computation and Language 2025-01-22 v1

Abstract

A number of automatic evaluation metrics have been proposed for natural language generation systems. The most common approach to automatic evaluation is the use of a reference-based metric that compares the model's output with gold-standard references written by humans. However, it is expensive to create such references, and for some tasks, such as response generation in dialogue, creating references is not a simple matter. Therefore, various reference-free metrics have been developed in recent years. In this survey, which intends to cover the full breadth of all NLG tasks, we investigate the most commonly used approaches, their application, and their other uses beyond evaluating models. The survey concludes by highlighting some promising directions for future research.

Keywords

Cite

@article{arxiv.2501.12011,
  title  = {Reference-free Evaluation Metrics for Text Generation: A Survey},
  author = {Takumi Ito and Kees van Deemter and Jun Suzuki},
  journal= {arXiv preprint arXiv:2501.12011},
  year   = {2025}
}

Comments

Work in progress

R2 v1 2026-06-28T21:12:15.312Z