search-arena-v1-7k

## Overview

This dataset contains 7k leaderboard conversation votes collected from [Search Arena](https://lmarena.ai/?search) between March 18, 2025 and April 13, 2025. All entries have been redacted for PII and sensitive user information to ensure privacy.

Each data point includes:
- Two model responses (`messages_a` and `messages_b`)
- The human vote result
- A timestamp
- Full system metadata, LLM + web search trace, and post-processed metadata for controlled experiments (`conv_meta`)

To reproduce the leaderboard results and analyses:
- Check out the [Colab notebook](https://colab.research.google.com/drive/1h7rR7rhePBPuIfaWsVNlW87kv3DLibPS?usp=sharing) for a step-by-step walkthrough.
- A companion [blog post](https://blog.lmarena.ai/blog/2025/search-arena) will provide deeper insights and commentary on the dataset and evaluation process.

## License
User prompts are licensed under CC-BY-4.0, and model outputs are governed by the terms of use set by the respective model providers.

## Citation
```bibtex
@misc{searcharena2025,
title = {Introducing the Search Arena: Evaluating Search-Enabled AI},
url = {https://blog.lmarena.ai/blog/2025/search-arena/},
author = {Mihran Miroyan*, Tsung-Han Wu*, Logan Kenneth King, Tianle Li, Anastasios N. Angelopoulos, Wei-Lin Chiang, Narges Norouzi, Joseph E. Gonzalez},
month = {April},
year = {2025}
}

@misc{chiang2024chatbot,
title={Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference},
author={Wei-Lin Chiang and Lianmin Zheng and Ying Sheng and Anastasios Nikolas Angelopoulos and Tianle Li and Dacheng Li and Hao Zhang and Banghua Zhu and Michael Jordan and Joseph E. Gonzalez and Ion Stoica},
year={2024},
eprint={2403.04132},
archivePrefix={arXiv},
primaryClass={cs.AI}
}
```

## 数据集概览
本数据集包含2025年3月18日至2025年4月13日期间，从[搜索竞技场（Search Arena）](https://lmarena.ai/?search)平台采集的7000条排行榜对话投票数据。所有条目均已对个人可识别信息（PII）及敏感用户信息进行脱敏处理，以保障用户隐私。

每条数据样本包含以下内容：
- 两份模型回复（`messages_a`与`messages_b`）
- 人工投票结果
- 时间戳
- 完整系统元数据、大语言模型（LLM）+网页搜索溯源记录，以及用于可控实验的后处理元数据（`conv_meta`）

若要复现该排行榜的实验结果与分析过程：
- 可参阅[Colab笔记本（Colab notebook）](https://colab.research.google.com/drive/1h7rR7rhePBPuIfaWsVNlW87kv3DLibPS?usp=sharing)获取详细分步操作指南。
- 配套的[博客文章（blog post）](https://blog.lmarena.ai/blog/2025/search-arena)将针对本数据集与评估流程提供更深入的解读与评述。

## 使用许可
用户提示语采用CC-BY-4.0许可协议，模型输出内容需遵循对应模型服务商的使用条款。

## 引用规范
可采用以下BibTeX格式进行引用：
bibtex
@misc{searcharena2025,
title = {Introducing the Search Arena: Evaluating Search-Enabled AI},
url = {https://blog.lmarena.ai/blog/2025/search-arena/},
author = {Mihran Miroyan*, Tsung-Han Wu*, Logan Kenneth King, Tianle Li, Anastasios N. Angelopoulos, Wei-Lin Chiang, Narges Norouzi, Joseph E. Gonzalez},
month = {4月},
year = {2025}
}

@misc{chiang2024chatbot,
title={Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference},
author={Wei-Lin Chiang and Lianmin Zheng and Ying Sheng and Anastasios Nikolas Angelopoulos and Tianle Li and Dacheng Li and Hao Zhang and Banghua Zhu and Michael Jordan and Joseph E. Gonzalez and Ion Stoica},
year={2024},
eprint={2403.04132},
archivePrefix={arXiv},
primaryClass={cs.AI}
}

搜集汇总

背景与挑战

背景概述

该数据集包含从Search Arena收集的7k条对话投票数据，时间跨度为2025年3月18日至4月13日，已进行隐私处理。每个条目包含两个模型响应、人类投票结果、时间戳及完整的元数据，适用于评估搜索增强型AI。