Metraipolis › archive › dc_a26bb6498db0

ContraVis: Evidence-Grounded Visual Analytics for Contradiction Review in Legal Contracts — arXiv:2609.27014

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.27014
License (as archived)
CC0-1.0
Archived
2026-10-08T10:05:27.335Z
SHA-256 of the archived text
9aa19576d51e2235830af4e7407bc903b8289518ef2b364a38bbc1f507fdcc30
Stable URL of this page
https://metraipolis.com/documento/dc_a26bb6498db0

How to cite

ContraVis: Evidence-Grounded Visual Analytics for Contradiction Review in Legal Contracts — arXiv:2609.27014 — arXiv (en), https://arxiv.org/abs/2609.27014 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a26bb6498db0 (Metraipolis archive dc_a26bb6498db0, sha256 9aa19576d51e2235830af4e7407bc903b8289518ef2b364a38bbc1f507fdcc30)
BibTeX
@misc{dca26bb6498db0,
  title = {ContraVis: Evidence-Grounded Visual Analytics for Contradiction Review in Legal Contracts — arXiv:2609.27014},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.27014},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a26bb6498db0; sha256 9aa19576d51e2235830af4e7407bc903b8289518ef2b364a38bbc1f507fdcc30},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.27014. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-24 in cs.CL).
Categorie arXiv: Human-Computer Interaction (cs.HC) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.27014 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-08T09:11:49.673Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).