Evaluation Metrics in the Era of GPT-4: Reliably Evaluating Large Language Models on Sequence to Sequence Tasks
Submission Type: Regular Short Paper
Submission Track: Resources and Evaluation
Submission Track 2: Theme Track: Large Language Models and the Future of NLP
Keywords: evaluation, human evaluation, LLM, summarization, simplification, grammatical error correction, ChatGPT, GPT-4, Sequence to sequence
TL;DR: An evaluation study of Large Language Models using automatic metrics, human evaluation, and model-to-model evaluation with GPT-4.
Abstract: Large Language Models (LLMs) evaluation is a patchy and inconsistent landscape, and it is becoming clear that the quality of automatic evaluation metrics is not keeping up with the pace of development of generative models. We aim to improve the understanding of current models' performance by providing a preliminary and hybrid evaluation on a range of open and closed-source generative LLMs on three NLP benchmarks: text summarisation, text simplification and grammatical error correction (GEC), using both automatic and human evaluation. We also explore the potential of the recently released GPT-4 to act as an evaluator. We find that ChatGPT consistently outperforms many other popular models according to human reviewers on the majority of metrics, while scoring much more poorly when using classic automatic evaluation metrics. We also find that human reviewers rate the gold reference as much worse than the best models' outputs, indicating the poor quality of many popular benchmarks. Finally, we find that GPT-4 is capable of ranking models' outputs in a way which aligns reasonably closely to human judgement despite task-specific variations, with a lower alignment in the GEC task.
Submission Number: 1504
Loading