Claude Opus 4.7 demonstrates strong substantive accuracy on BigLaw Bench for Harvey, scoring 90.9% at high effort with better reasoning calibration on review tables and noticeably smarter handling of ambiguous document editing tasks.
在法律文档处理中达到90.9%的准确率，特别是在处理模糊文档编辑任务时的智能提升，展示了AI在专业领域的深度应用能力，这种进步将极大扩展AI在法律和合规领域的应用价值。
For the documents that matter most, it gets to 99–100% field accuracy, even out-performing expert human labelers on extraction tasks.
大多数人认为人工智能系统在文档提取任务上总会落后于人类专家，尤其是对于复杂文档。但作者声称Deep Extract可以达到甚至超过人类专家的准确率(99-100%)，这是一个相当大胆的断言，挑战了AI在文档处理领域无法超越人类能力的共识。
Learning heterogeneous graph embedding for Chinese legal document similarity
The paper proposes L-HetGRL, an unsupervised approach using a legal heterogeneous graph and incorporating legal domain-specific knowledge, to improve Legal Document Similarity Measurement (LDSM) with superior performance compared to other methods.