PAKTON让非法律专家也能高效审查长篇合同。
PAKTON: A Multi-Agent Framework for Question Answering in Long Legal Agreements
- 多智能体协作+检索增强生成，自动解析合同复杂条款。
- 在准确率、可解释性等指标上超越通用模型和预训练模型。
- 完全开源，保护隐私，适合法律科技与AI研究者使用。
合同审查是一项复杂且耗时的任务，通常需要专业法律知识，对非专业人士不友好。法律解释常含歧义，判断多依赖主观判断。此外，合同具有保密性，限制了专有模型的应用，需依赖开源方案。为此，我们提出PAKTON：一个全开源、端到端、可插拔的多智能体框架。PAKTON通过协作式智能体流程与新颖的检索增强生成（RAG）组件，实现更易用、可适应、隐私友好的自动化合同审查。实验表明，相较于通用模型与预训练模型，PAKTON在预测准确率、检索性能、可解释性、完整性及依据充分性方面均表现更优，经人工评估与自动指标双重验证。
原文摘要 · Abstract (English)
Contract review is a complex and time-intensive task that typically demands specialized legal expertise, rendering it largely inaccessible to non-experts. Moreover, legal interpretation is rarely straightforward-ambiguity is pervasive, and judgments often hinge on subjective assessments. Compounding these challenges, contracts are usually confidential, restricting their use with proprietary models and necessitating reliance on open-source alternatives. To address these challenges, we introduce PAKTON: a fully open-source, end-to-end, multi-agent framework with plug-and-play capabilities. PAKTON is designed to handle the complexities of contract analysis through collaborative agent workflows and a novel retrieval-augmented generation (RAG) component, enabling automated legal document review that is more accessible, adaptable, and privacy-preserving. Experiments demonstrate that PAKTON outperforms both general-purpose and pretrained models in predictive accuracy, retrieval performance, explainability, completeness, and grounded justifications as evaluated through a human study and validated with automated metrics.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。