Llama-3-70b-battles

**Chatbot Arena user conversations between Llama-3-70b VS GPT-4-1025 or Llama-3-70b VS Claude-3-Opus with user preference votes.** Single turn. Excludes ties.

Used in [Llama Data Analysis blog post](https://blog.lmarena.ai/blog/2024/llama3/) and "VibeCheck: Discover and Quantify Qualitative Differences in Large Language Models" ([Paper](https://arxiv.org/abs/2410.12851), [Code](https://github.com/lisadunlap/VibeCheck)).

## Citation
```
@article{dunlap_vibecheck,
title={VibeCheck: Discover and Quantify Qualitative Differences in Large Language Models},
author={Lisa Dunlap and Krishna Mandal and Trevor Darrell and Jacob Steinhardt and Joseph E Gonzalez},
journal={arXiv preprint arXiv:2312.02974},
year={2024},
archivePrefix={arXiv},
primaryClass={cs.LG},
url={https://arxiv.org/abs/2410.12851},
}
```
```
@misc{llama3arena2024,
title = {What’s up with Llama 3? Arena data analysis},
url = {https://blog.lmarena.ai/blog/2024/llama3/},
author = {Lisa Dunlap, Evan Frick, Tianle Li, Isaac Ong, Joseph E. Gonzalez, Wei-Lin Chiang},
month = {May},
year = {2024}
}
```
---
license: apache-2.0
---

**包含用户偏好投票的聊天机器人竞技场（Chatbot Arena）单轮对话数据集，对战组合为Llama-3-70b对阵GPT-4-1025，或Llama-3-70b对阵Claude-3-Opus，且已剔除平局样本。

本数据集已被应用于《Llama 3近况解析：竞技场数据分析》博客博文（[链接](https://blog.lmarena.ai/blog/2024/llama3/)）以及论文《VibeCheck：探索并量化大语言模型（Large Language Model）的定性差异》（[论文链接](https://arxiv.org/abs/2410.12851)、[代码仓库链接](https://github.com/lisadunlap/VibeCheck)）。

## 引用

@article{dunlap_vibecheck,
title={VibeCheck：探索并量化大语言模型的定性差异},
author={Lisa Dunlap and Krishna Mandal and Trevor Darrell and Jacob Steinhardt and Joseph E Gonzalez},
journal={arXiv预印本},
year={2024},
archivePrefix={arXiv},
primaryClass={cs.LG},
url={https://arxiv.org/abs/2410.12851},
}

@misc{llama3arena2024,
title={Llama 3近况解析：竞技场数据分析},
url={https://blog.lmarena.ai/blog/2024/llama3/},
author={Lisa Dunlap, Evan Frick, Tianle Li, Isaac Ong, Joseph E. Gonzalez, Wei-Lin Chiang},
month={May},
year={2024}
}

---
许可证：Apache 2.0
---