Check-Eval: A Checklist-based Approach for Evaluating Text Quality

Evaluating the quality of text generated by large language models (LLMs) remains a significant challenge. Traditional metrics often fail to align well with human judgments, particularly in tasks requiring creativity and nuance. In this paper, we propose $\text{textsc}Check-Eval$, a novel evaluation framework leveraging LLMs to assess the quality of generated text through a checklist-based approach. $\text{textsc}Check-Eval$ can be employed as both a reference-free and reference-dependent evaluation method, providing a structured and interpretable assessment of text quality. The framework consists of two main stages: checklist generation and checklist evaluation. We validate $\text{textsc}Check-Eval$ on two benchmark datasets: Portuguese Legal Semantic Textual Similarity and $\text{textsc}SummEval$. Our results demonstrate that $\text{textsc}Check-Eval$ achieves higher correlations with human judgments compared to existing metrics, such as $\text{textsc}G-Eval$ and $\text{textsc}GPTScore$, underscoring its potential as a more reliable and effective evaluation framework for natural language generation tasks. The code for our experiments is available at \url{https://anonymous.4open.science/r/check-eval-0DB4}