构建多语言法律摘要数据集，提升瑞士判例检索效率
Unlocking Legal Knowledge: A Multilingual Dataset for Judicial Summarization in Switzerland
- 构建20,000份瑞士联邦最高法院判决的德法意三语摘要数据集
- 微调模型在词汇相似度上表现良好，大模型生成更准确连贯的摘要
- 适合跨语言法律文本处理与AI辅助司法研究者使用
法律研究依赖于案情摘要（headnotes），帮助律师快速识别相关判例。然而，由于人工标注成本高，许多判决缺乏摘要。为此，我们推出了瑞士标志性判决摘要数据集（SLDS），包含20,000份来自瑞士联邦最高法院的判决，每份均配有德语、法语和意大利语的摘要。SLDS有望显著提升法律信息获取效率，推动瑞士法律研究变革。我们对Qwen2.5、Llama 3.2、Phi-3.5等开源模型进行微调，并与GPT-4o、Claude 3.5 Sonnet及DeepSeek R1等大型通用与推理优化模型对比。通过LLM-as-a-Judge框架评估发现，微调模型在词汇相似度上表现优异，而更大模型生成的摘要更具法律准确性与连贯性。值得注意的是，推理型模型未展现出稳定优势，表明该任务中事实精确性比深度推理更重要。SLDS已按CC BY 4.0许可发布，以支持未来跨语言法律摘要研究。
原文摘要 · Abstract (English)
Legal research depends on headnotes: concise summaries that help lawyers quickly identify relevant cases. Yet, many court decisions lack them due to the high cost of manual annotation. To address this gap, we introduce the Swiss Landmark Decisions Summarization (SLDS) dataset containing 20K rulings from the Swiss Federal Supreme Court, each with headnotes in German, French, and Italian. SLDS has the potential to significantly improve access to legal information and transform legal research in Switzerland. We fine-tune open models (Qwen2.5, Llama 3.2, Phi-3.5) and compare them to larger general-purpose and reasoning-tuned LLMs, including GPT-4o, Claude 3.5 Sonnet, and the open-source DeepSeek R1. Using an LLM-as-a-Judge framework, we find that fine-tuned models perform well in terms of lexical similarity, while larger models generate more legally accurate and coherent summaries. Interestingly, reasoning-focused models show no consistent benefit, suggesting that factual precision is more important than deep reasoning in this task. We release SLDS under a CC BY 4.0 license to support future research in cross-lingual legal summarization.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。