System assists lawyers in spotting contradictions in complex contracts
ContraVis: Evidence-Grounded Visual Analytics for Contradiction Review in Legal Contracts
Human-Computer InteractionComputation and Language
Summary
Legal contracts can be complicated and sometimes contain contradictory statements that are hard to find because they may be spread out and connected in subtle ways. Contradiction analysis usually requires careful human review supported by trustable evidence. The authors created a tool called ContraVis that helps people analyze contracts by showing the connections and references between contract parts visually while using language models to suggest contradictions. Their tests showed this approach found more contradictions than language models alone, helping lawyers verify these issues with clear evidence.
What this means in practice
- •For contract lawyers: Support detailed contradiction review in lengthy contracts by combining AI suggestions with interactive evidence visualization to improve accuracy.
- •For legal tech developers: Enhance contract review software with graph-based visualizations that help users explore contractual references and validate possible contradictions.
Authors
Luis Sante, Paula Lima, Mariana Rocha, Jorge Poco
Abstract
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.