INSTRUCTSCORE: Towards Explainable Text Generation Evaluation with Automatic Feedback

Wenda Xu, Danqing Wang, Liangming Pan, Zhenqiao Song, Markus Freitag, William Yang Wang, Lei Li

Submission Type: Regular Long Paper

Submission Track: Natural Language Generation

Keywords: Text generation evaluation, Explainable metric

Abstract: Automatically evaluating the quality of language generation is critical. Although recent learned metrics show high correlation with human judgement, these metrics do not provide explicit explanation of their verdict, nor associate the scores with defects in the generated text. To address this limitation, we present INSTRUCTSCORE, a fine-grained explainable evaluation metric for text generation. By harnessing both explicit human instruction and the implicit knowledge of GPT-4, we fine-tune a text evaluation metric based on LLaMA, producing both a score for generated text and a human readable diagnostic report. We evaluate INSTRUCTSCORE on a variety of generation tasks, including translation, captioning, data-to-text, and commonsense generation. Experiments show that our 7B model surpasses all other unsupervised metrics, including those based on 175B GPT-3 and GPT-4. Surprisingly, our INSTRUCTSCORE, even without direct supervision from human-rated data, achieves performance levels on par with state-of-the-art metrics like COMET22, which were fine-tuned on human ratings.

Submission Number: 2729