Is GPT-4 a reliable rater? Evaluating Consistency in GPT-4 Text Ratings
arXiv:2308.02575 · doi:10.3389/feduc.2023.1272229
Abstract
This study investigates the consistency of feedback ratings generated by OpenAI's GPT-4, a state-of-the-art artificial intelligence language model, across multiple iterations, time spans and stylistic variations. The model rated responses to tasks within the Higher Education (HE) subject domain of macroeconomics in terms of their content and style. Statistical analysis was conducted in order to learn more about the interrater reliability, consistency of the ratings across iterations and the correlation between ratings in terms of content and style. The results revealed a high interrater reliability with ICC scores ranging between 0.94 and 0.99 for different timespans, suggesting that GPT-4 is capable of generating consistent ratings across repetitions with a clear prompt. Style and content ratings show a high correlation of 0.87. When applying a non-adequate style the average content ratings remained constant, while style ratings decreased, which indicates that the large language model (LLM) effectively distinguishes between these two criteria during evaluation. The prompt used in this study is furthermore presented and explained. Further research is necessary to assess the robustness and reliability of AI models in various use cases.
14 pages, 7 tables, 1 figure
References in corpus (10)
- Emergent Abilities of Large Language Models
- A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPT
- How is ChatGPT's behavior changing over time?
- Prompt Injection attack against LLM-integrated Applications
- Ignore Previous Prompt: Attack Techniques For Language Models
- Prompting GPT-3 To Be Reliable
- Discovering Language Model Behaviors with Model-Written Evaluations
- Boosting Theory-of-Mind Performance in Large Language Models via Prompting
- Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?
- TELeR: A General Taxonomy of LLM Prompts for Benchmarking Complex Tasks