发表机构
Fundação Getulio Vargas (FGV); School of Applied Mathematics（热图利奥·瓦加斯基金会（FGV）; 应用数学学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对法律合同中跨条款矛盾审查，提出基于证据的可视分析系统ContraVis，利用类型化段落图调节LLM推理并支持人机协同，实验证明其随合同长度增长更有效恢复矛盾。
AI 中文摘要
法律合同是结构复杂的文档，其中矛盾可能出现在相距较远且相互关联的条款之间。尽管大型语言模型（LLMs）提升了法律语言理解能力，矛盾分析仍然是一项以人为中心、基于证据的审查任务。我们提出了ContraVis，一个用于法律合同中人在回路矛盾分析的可视分析系统。该系统将合同建模为类型化段落图，该图结合了显式的合同引用与段落之间的语义关系。该图扮演双重角色：它调节LLM的推理，并作为分析师探索的交互式表示，使模型上下文与人工检查在协调视图中保持一致。在一项受控比较中，随着合同长度的增加，基于图的推理比独立的LLM分析恢复了更多注入的矛盾，同时浮现出额外的候选供分析师验证。一项与合同领域律师进行的形成性研究表明，上下文中的证据比较支持矛盾验证，我们提炼出基于证据、LLM辅助文档审查的设计启示。
英文摘要
Legal contracts are structurally complex documents in which contradictions may emerge across distant and interconnected provisions. Although large language models (LLMs) improve legal language understanding, contradiction analysis remains a human-centered and evidence-grounded review task. We present ContraVis, a visual analytics system for human-in-the-loop contradiction analysis in legal contracts. The system models contracts as typed paragraph graphs that combine explicit contractual references with semantic relationships between paragraphs. This graph plays a dual role: it conditions LLM reasoning and serves as the interactive representation the analyst explores, keeping model context and human inspection aligned across coordinated views. In a controlled comparison, graph-conditioned reasoning recovered more injected contradictions than standalone LLM analysis as contract length grew, while surfacing additional candidates for analyst validation. A formative study with contract-domain lawyers indicated that in-context evidence comparison supported contradiction validation, and we distill design implications for evidence-grounded, LLM-assisted document review.
Comments8 pages, 4 figures, SIBGRAPI 2026
