跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 2026-10-18AI 評分45

真實場景中的法律指引:用戶如何在大語言模型對話中尋求法律協助

Legal Guidance in the Wild: How Users Seek Legal Help in Real-World LLM Conversations

AI 導讀

這項研究分析真實世界的大語言模型對話中用戶尋求法律指引的方式,建立分類體系並標註 2,122 段 WildChat 對話。研究另發布經人工審核、包含 200 段對話的評測集,並訓練及評估用於識別法律指引請求和分類法律主題的小型分類器。相關數據集、模型檢查點及評估程式碼均已公開。

正文

We study how people seek legal guidance in real-world LLM conversations. We introduce a taxonomy, annotate 2,122 WildChat conversations, and release a human-reviewed evaluation set of 200 conversations. We also train and evaluate smaller classifiers to detect guidance-seeking requests and classify their legal topics.

The datasets, model checkpoints, and evaluation code are publicly available. We hope these resources support further research into legal guidance seeking in conversational AI.

Happy to discuss the work and hear your thoughts!

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co