From 00f8dd3dc960fb293d23eb1704521211af7dc956 Mon Sep 17 00:00:00 2001 From: Xinyu Hu Date: Thu, 27 Jun 2024 13:18:27 +0000 Subject: [PATCH] Update README.md --- README.md | 74 ++++++++++++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 71 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index 7b95401..7ac5cdf 100644 --- a/README.md +++ b/README.md @@ -1,3 +1,71 @@ ---- -license: apache-2.0 ---- +--- +license: apache-2.0 +--- +# Themis + +Paper: https://arxiv.org/abs/2406.18365 + +Github: https://github.com/PKU-ONELab/Themis + +## Introduction + +We propose **Themis**, an 8B-parameter large language model (LLM) specifically designed and trained for NLG evaluation with more comprehensive capabilities. + +Our Themis can evaluate various NLG tasks, including uncommon ones like question-answering evaluation (**Versatility**), in a reference-free manner (**Independence**). Moreover, it allows for specific and customized evaluation aspects and criteria, including overall quality and more fine-grained aspects (**Flexibility**), and its evaluation contains corresponding analysis and explanation together with the rating (**Interpretability**). + +We believe that an ideal evaluator should be convenient to use and possess these characteristics. The comparison between related methods and Themis is shown in the table below. + +| Method | Versatility | Independence | Flexibility | Interpretability | Open-source | +| :---------------: | :---------: | :----------: | :---------: | :--------------: | :---------: | +| UniEval | ❌ | ❌ | ✔️ | ❌ | ✔️ | +| G-Eval | ✔️ | ✔️ | ✔️ | ✔️ | ❌ | +| X-Eval | ✔️ | ❌ | ✔️ | ❌ | ❌ | +| Prometheus | ✔️ | ❌ | ✔️ | ✔️ | ✔️ | +| Auto-J | ✔️ | ✔️ | ❌ | ✔️ | ✔️ | +| InstructScore | ✔️ | ❌ | ❌ | ✔️ | ✔️ | +| TIGERScore | ✔️ | ✔️ | ❌ | ✔️ | ✔️ | +| **Themis (Ours)** | ✔️ | ✔️ | ✔️ | ✔️ | ✔️ | + +## Performance + +We implement experiments on several common NLG evaluation tasks and datasets to compare our Themis with other methods, including SummEval for summarization, Topical-Chat for dialogue response generation, SFRES&SFHOT for data-to-text, QAGS for factuality, MANS for story generation, and WMT23 zh-en for machine translation. Experimental results show that our Themis achieves better overall evaluation performance over other evaluation models, including GPT-4. + +| Method | SummEval | Topical-Chat | SFHOT&SFRES | QAGS | MANS | WMT23 | Average $\rho$ | +| -------------------- | :-------: | :----------: | :---------: | :-------: | :-------: | :-------: | :------------: | +| BLEU | 0.075 | 0.388 | 0.024 | - | 0.032 | 0.021 | - | +| ROUGE | 0.152 | 0.412 | 0.101 | - | -0.002 | 0.151 | - | +| BARTScore | 0.329 | 0.086 | 0.208 | 0.425 | 0.350 | 0.118 | 0.253 | +| BERTScore | 0.231 | 0.394 | 0.139 | - | 0.285 | 0.219 | - | +| BLEURT | 0.152 | 0.388 | 0.244 | - | 0.138 | 0.263 | - | +| CometKiwi | 0.228 | 0.340 | 0.251 | 0.094 | 0.251 | 0.343 | 0.251 | +| UniEval | 0.474 | 0.577 | 0.282 | - | - | - | - | +| G-Eval (GPT-3.5) | 0.409 | 0.585 | - | 0.461 | - | - | - | +| G-Eval (GPT-4) | 0.523 | 0.588 | - | 0.611 | - | - | - | +| GPT-3.5 Turbo | 0.416 | 0.578 | 0.306 | 0.431 | 0.328 | 0.347 | 0.401 | +| GPT-4 Turbo | 0.511 | **0.746** | 0.320 | 0.637 | 0.473 | **0.437** | 0.521 | +| X-Eval | 0.480 | 0.605 | 0.303 | 0.578 | - | - | - | +| Prometheus-13B | 0.163 | 0.434 | 0.173 | - | 0.007 | 0.129 | - | +| Auto-J-13B | 0.198 | 0.425 | 0.141 | 0.226 | 0.380 | 0.104 | 0.246 | +| TIGERScore-13B | 0.384 | 0.346 | 0.200 | 0.504 | 0.231 | 0.248 | 0.319 | +| InstructScore-7B | 0.258 | 0.241 | 0.247 | - | 0.298 | 0.219 | - | +| **Themis-8B (ours)** | **0.553** | 0.725 | **0.333** | **0.684** | **0.551** | 0.405 | **0.542** | + +We further conduct more in-depth analyses, including generalization tests on unseen tasks like the instruction-following evaluation as well as aspect-targeted perturbation tests, and our Themis also exhibits superior evaluation performance. For more experimental results and details, please refer to our paper. + +## Requirements and Usage + +Please refer to our [github repo](https://github.com/PKU-ONELab/Themis) for more details. + +## Citation + +``` +@misc{hu2024themisflexibleinterpretablenlg, + title={Themis: Towards Flexible and Interpretable NLG Evaluation}, + author={Xinyu Hu and Li Lin and Mingqi Gao and Xunjian Yin and Xiaojun Wan}, + year={2024}, + eprint={2406.18365}, + archivePrefix={arXiv}, + primaryClass={cs.CL}, + url={https://arxiv.org/abs/2406.18365}, +} +``` \ No newline at end of file