Recently, using a powerful proprietary Large Language Model (LLM) (e.g., GPT-4) as an evaluator for long-form responses has become the de facto standard. However, for practitioners with large-scale evaluation tasks and custom criteria in consideration (e.g., child-readability), using proprietary LLMs as an evaluator is unreliable due to the closed-source nature, uncontrolled versioning, and prohibitive costs. In this work, we propose Prometheus, a fully open-source LLM that is on par with GPT-4's evaluation capabilities when the appropriate reference materials (reference answer, score rubric) are accompanied. We first construct the Feedback Collection, a new dataset that consists of 1K fine-grained score rubrics, 20K instructions, and 100K responses and language feedback generated by GPT-4. Using the Feedback Collection, we train Prometheus, a 13B evaluator LLM that can assess any given long-form text based on customized score rubric provided by the user. Experimental results show that Prometheus scores a Pearson correlation of 0.897 with human evaluators when evaluating with 45 customized score rubrics, which is on par with GPT-4 (0.882), and greatly outperforms ChatGPT (0.392). Furthermore, measuring correlation with GPT-4 with 1222 customized score rubrics across four benchmarks (MT Bench, Vicuna Bench, Feedback Bench, Flask Eval) shows similar trends, bolstering Prometheus's capability as an evaluator LLM. Lastly, Prometheus achieves the highest accuracy on two human preference benchmarks (HHH Alignment & MT Bench Human Judgment) compared to open-sourced reward models explicitly trained on human preference datasets, highlighting its potential as an universal reward model. We open-source our code, dataset, and model at https://kaistai.github.io/prometheus/.
The paper introduces Prometheus, a 13B parameter open-source language model designed for fine-grained evaluation, rivaling proprietary models like GPT-4.
Prometheus leverages the Feedback Collection dataset, consisting of 1K fine-grained score rubrics, 20K instructions, and 100K responses, to enable nuanced text evaluation.
Experimental validation shows Prometheus matches or exceeds human evaluators and GPT-4 in feedback quality and correlation, and outperforms other models in terms of being a universal reward model.
The study highlights Prometheus's potential in making high-quality evaluation tools more accessible and suggests its utility in various AI training methodologies.
Recent advances in NLP have positioned LLMs as potent tools for evaluating machine-generated text. However, reliance on proprietary models like GPT-4 presents challenges including lack of transparency, version control issues, and financial barriers. Addressing these concerns, this paper introduces Prometheus, a 13B parameter open-source language model designed to rival the evaluation capabilities of GPT-4. Prometheus, leveraging the newly compiled Feedback Collection dataset, demonstrates remarkable proficiency in evaluating long-form responses across diverse custom score rubrics, showcasing its potential as a versatile and accessible evaluator.
The Feedback Collection dataset stands out for its unique architecture, designed specifically to enhance fine-grained evaluation capabilities of LLMs. Consisting of 1K fine-grained score rubrics, 20K instructions, and 100K responses with language feedback generated using GPT-4, it introduces a sophisticated framework for instruction-based evaluation. Each dataset instance comprises multiple components, including sophisticated rubrics and reference answers, to enable nuanced understanding and evaluation of text responses. This design not only facilitates detailed feedback generation but also quantitatively rates responses, paving the way for comprehensive and tailored text evaluation.
Prometheus’s evaluation prowess was rigorously tested across various benchmarks and compared with human evaluators as well as GPT-4 and ChatGPT models. Key findings are as follows:
These results underscore Prometheus’s adeptness not only in emulating human evaluation standards but also in its utility as a universal reward model, offering insights into its potential applications in model training and development.
Prometheus challenges the prevailing dependence on proprietary LLMs for text evaluation by offering an open-source alternative that does not sacrifice performance. The inclusion of reference materials such as score rubrics and reference answers proves vital in its success, suggesting avenues for further enhancing LLM evaluators. Additionally, the performance on ranking grading schemes suggests Prometheus's adaptability as a reward model for various AI training methodologies, marking a significant stride toward developing versatile, transparent, and accessible evaluation tools in NLP.
The open-sourcing of Prometheus, along with the Feedback Collection dataset, not only democratizes access to high-quality evaluation tools but also encourages community collaboration in refining and expanding upon this foundational work. Future research could explore domain-specific evaluator models, further diversify evaluation criteria, and integrate Prometheus into broader AI training and development workflows, paving the way for innovative applications and methodologies in artificial intelligence research.
Acknowledgeably, this research initiates a crucial discussion on transparency, autonomy, and accessibility in AI evaluation, setting a precedent for future endeavors in the field. Prometheus not only signifies a step forward in LLM evolution but also embodies the collaborative spirit essential for sustainable progress in AI research and development.
Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality, March 2023. https://lmsys.org/blog/2023-03-30-vicuna/.
Alpacaeval: An automatic evaluator of instruction-following models. https://github.com/tatsu-lab/alpaca_eval
Chin-Yew Lin. ROUGE: A package for automatic evaluation of summaries. In Text Summarization Branches Out, pp. 74–81, Barcelona, Spain, July 2004a. Association for Computational Linguistics. https://aclanthology.org/W04-1013.
Bleurt: Learning robust metrics for text generation. In Annual Meeting of the Association for Computational Linguistics, 2020. https://api.semanticscholar.org/CorpusID:215548699.
Selfee: Iterative self-revising llm empowered by self-feedback generation. Blog post, May 2023a. https://kaistai.github.io/SelFee/.
BARTScore: Evaluating generated text as text generation. In A. Beygelzimer, Y. Dauphin, P. Liang, and J. Wortman Vaughan (eds.), Advances in Neural Information Processing Systems, 2021. https://openreview.net/forum?id=5Ya8PbvpZ9.