Is ChatGPT a Good NLG Evaluator? A Preliminary Study

• URL: http://arxiv.org/abs/2303.04048v3
• Date: Tue, 24 Oct 2023 14:56:51 GMT
• Title: Is ChatGPT a Good NLG Evaluator? A Preliminary Study
• Authors: Jiaan Wang, Yunlong Liang, Fandong Meng, Zengkui Sun, Haoxiang Shi, Zhixu Li, Jinan Xu, Jianfeng Qu, Jie Zhou
• Abstract summary: We provide a preliminary meta-evaluation on ChatGPT to show its reliability as an NLG metric. Experimental results show that compared with previous automatic metrics, ChatGPT achieves state-of-the-art or competitive correlation with human judgments. We hope our preliminary study could prompt the emergence of a general-purposed reliable NLG metric.
• Score: 121.77986688862302
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recently, the emergence of ChatGPT has attracted wide attention from the computational linguistics community. Many prior studies have shown that ChatGPT achieves remarkable performance on various NLP tasks in terms of automatic evaluation metrics. However, the ability of ChatGPT to serve as an evaluation metric is still underexplored. Considering assessing the quality of natural language generation (NLG) models is an arduous task and NLG metrics notoriously show their poor correlation with human judgments, we wonder whether ChatGPT is a good NLG evaluation metric. In this report, we provide a preliminary meta-evaluation on ChatGPT to show its reliability as an NLG metric. In detail, we regard ChatGPT as a human evaluator and give task-specific (e.g., summarization) and aspect-specific (e.g., relevance) instruction to prompt ChatGPT to evaluate the generated results of NLG models. We conduct experiments on five NLG meta-evaluation datasets (including summarization, story generation and data-to-text tasks). Experimental results show that compared with previous automatic metrics, ChatGPT achieves state-of-the-art or competitive correlation with human judgments in most cases. In addition, we find that the effectiveness of the ChatGPT evaluator might be influenced by the creation method of the meta-evaluation datasets. For the meta-evaluation datasets which are created greatly depending on the reference and thus are biased, the ChatGPT evaluator might lose its effectiveness. We hope our preliminary study could prompt the emergence of a general-purposed reliable NLG metric.

Related papers

• Using ChatGPT to Score Essays and Short-Form Constructed Responses [0.0]
  Investigation focused on various prediction models, including linear regression, random forest, gradient boost, and boost. ChatGPT's performance was evaluated against human raters using quadratic weighted kappa (QWK) metrics. Study concludes that ChatGPT can complement human scoring but requires additional development to be reliable for high-stakes assessments.
  arXiv  Detail & Related papers  (2024-08-18T16:51:28Z)
• Eval-GCSC: A New Metric for Evaluating ChatGPT's Performance in Chinese Spelling Correction [60.32771192285546]
  ChatGPT has demonstrated impressive performance in various downstream tasks. In the Chinese Spelling Correction (CSC) task, we observe a discrepancy: while ChatGPT performs well under human evaluation, it scores poorly according to traditional metrics. This paper proposes a new evaluation metric: Eval-GCSC. By incorporating word-level and semantic similarity judgments, it relaxes the stringent length and phonics constraints.
  arXiv  Detail & Related papers  (2023-11-14T14:56:33Z)
• Evaluating ChatGPT as a Recommender System: A Rigorous Approach [12.458752059072706]
  We propose a robust evaluation pipeline to assess ChatGPT's ability as an RS and post-process ChatGPT recommendations. We analyze the model's functionality in three settings: the Top-N Recommendation, the cold-start recommendation, and the re-ranking of a list of recommendations.
  arXiv  Detail & Related papers  (2023-09-07T10:13:09Z)
• A Systematic Study and Comprehensive Evaluation of ChatGPT on Benchmark Datasets [19.521390684403293]
  We present a thorough evaluation of ChatGPT's performance on diverse academic datasets. Specifically, we evaluate ChatGPT across 140 tasks and analyze 255K responses it generates in these datasets.
  arXiv  Detail & Related papers  (2023-05-29T12:37:21Z)
• ChatLog: Carefully Evaluating the Evolution of ChatGPT Across Time [54.18651663847874]
  ChatGPT has achieved great success and can be considered to have acquired an infrastructural status. Existing benchmarks encounter two challenges: (1) Disregard for periodical evaluation and (2) Lack of fine-grained features. We construct ChatLog, an ever-updating dataset with large-scale records of diverse long-form ChatGPT responses for 21 NLP benchmarks from March, 2023 to now.
  arXiv  Detail & Related papers  (2023-04-27T11:33:48Z)
• Evaluating ChatGPT's Information Extraction Capabilities: An Assessment of Performance, Explainability, Calibration, and Faithfulness [18.945934162722466]
  We focus on assessing the overall ability of ChatGPT using 7 fine-grained information extraction (IE) tasks. ChatGPT's performance in Standard-IE setting is poor, but it surprisingly exhibits excellent performance in the OpenIE setting. ChatGPT provides high-quality and trustworthy explanations for its decisions.
  arXiv  Detail & Related papers  (2023-04-23T12:33:18Z)
• G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment [64.01972723692587]
  We present G-Eval, a framework of using large language models with chain-of-thoughts (CoT) and a form-filling paradigm to assess the quality of NLG outputs. We show that G-Eval with GPT-4 as the backbone model achieves a Spearman correlation of 0.514 with human on summarization task, outperforming all previous methods by a large margin.
  arXiv  Detail & Related papers  (2023-03-29T12:46:54Z)
• Exploring ChatGPT's Ability to Rank Content: A Preliminary Study on Consistency with Human Preferences [6.821378903525802]
  ChatGPT has consistently demonstrated a remarkable level of accuracy and reliability in terms of content evaluation. A test set consisting of prompts is created, covering a wide range of use cases, and five models are utilized to generate corresponding responses. Results on the test set show that ChatGPT's ranking preferences are consistent with human to a certain extent.
  arXiv  Detail & Related papers  (2023-03-14T03:13:02Z)
• Can ChatGPT Understand Too? A Comparative Study on ChatGPT and Fine-tuned BERT [103.57103957631067]
  ChatGPT has attracted great attention, as it can generate fluent and high-quality responses to human inquiries. We evaluate ChatGPT's understanding ability by evaluating it on the most popular GLUE benchmark, and comparing it with 4 representative fine-tuned BERT-style models. We find that: 1) ChatGPT falls short in handling paraphrase and similarity tasks; 2) ChatGPT outperforms all BERT models on inference tasks by a large margin; 3) ChatGPT achieves comparable performance compared with BERT on sentiment analysis and question answering tasks.
  arXiv  Detail & Related papers  (2023-02-19T12:29:33Z)
• Is ChatGPT a General-Purpose Natural Language Processing Task Solver? [113.22611481694825]
  Large language models (LLMs) have demonstrated the ability to perform a variety of natural language processing (NLP) tasks zero-shot. Recently, the debut of ChatGPT has drawn a great deal of attention from the natural language processing (NLP) community. It is not yet known whether ChatGPT can serve as a generalist model that can perform many NLP tasks zero-shot.
  arXiv  Detail & Related papers  (2023-02-08T09:44:51Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.