用符号化方法让法律判决更准更快，还能全程可审计。
Accurate Legal Reasoning at Scale: Neuro-Symbolic Offloading and Structural Auditability for Robust Legal Adjudication
- 先用大模型把法律条文转成结构化图谱，再用确定性计算执行
- 推理错误率近乎为零，计算成本降低90%以上
- 适合对可靠性要求高的法律智能系统开发
法律文本常包含需复杂逻辑理解的条款。尽管前沿大推理模型（LRM）能描述这些条款，但生产系统受限于推理错误和高推理成本。我们提出消融智能（Amortized Intelligence），一种神经符号方法：仅用一次大模型将法律文本转换为确定性自治合约语言（DACL）——一种带类型的图结构中间表示。判决过程依赖于确定性图执行，并具备可视化的可审计追踪。相比运行时大模型基线（包括GPT-5.2和Gemini 3 Pro），基于DACL的代理实现近乎完美的结果一致性，缓解了概率模型中的“推理悬崖”问题。该系统在高吞吐工作流中将计算成本降低超过90%，同时满足法律裁决严格的可审计要求。
原文摘要 · Abstract (English)
Legal texts often contain computational legal clauses--provisions whose understanding requires complex logic. While frontier Large Reasoning Models (LRMs) can describe such clauses, building production-ready systems is limited by reasoning errors and the high cost of inference. We propose Amortized Intelligence, a neuro-symbolic approach where we use an LLM once to translate a legal text into Deterministic Autonomous Contract Language (DACL): a typed graph intermediate representation. Adjudication then relies on deterministic graph executions with a visually auditable trace. In comparison against runtime LRM baselines (including GPT-5.2 and Gemini 3 Pro), our DACL-based Agent achieves near-perfect consistency and mitigates the "reasoning cliff" observed in probabilistic models. The system reduces compute costs by over 90% in high-volume workflows while satisfying the strict auditability requirements of legal adjudication.
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。