解锁法律知识：面向瑞士司法摘要的多语言数据集
Unlocking Legal Knowledge: A Multilingual Dataset for Judicial Summarization in Switzerland
AI总结：
本文提出包含瑞士联邦最高法院2万份多语言裁决摘要的SLDS数据集，通过微调开源模型并与大型LLM对比发现，事实准确性比深度推理更能决定法律摘要的质量。
摘要：
法律研究依赖于裁判要旨：这些简明的摘要能帮助律师快速识别相关案例。然而，由于人工标注成本高昂，许多法院判决缺乏此类摘要。为弥补这一空白，我们引入了Swiss Landmark Decisions Summarization (SLDS) 数据集，其中包含来自瑞士联邦最高法院的2万份裁决，每份均附有德语、法语和意大利语的裁判要旨。SLDS有望显著提升法律信息的获取便利度，并变革瑞士的法律研究。我们对开源模型（Qwen2.5、Llama 3.2、Phi-3.5）进行了微调，并将其与更大型的通用及推理调优LLM进行比较，包括GPT-4o、Claude 3.5 Sonnet以及开源的DeepSeek R1。使用LLM-as-a-Judge框架，我们发现微调模型在词汇相似度方面表现良好，而更大型的模型则能生成法律上更准确、更连贯的摘要。有趣的是，侧重推理的模型并未表现出一致的益处，这表明在该任务中，事实准确性比深度推理更为重要。我们在CC BY 4.0许可下发布SLDS，以支持跨语言法律摘要的未来研究。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
