Accurate Legal Reasoning at Scale: Neuro-Symbolic Offloading and Structural Auditability for Robust Legal Adjudication
For legal AI systems requiring high accuracy and auditability, this work provides a cost-effective solution that mitigates reasoning errors in large language models.
The paper introduces Amortized Intelligence, a neuro-symbolic approach that translates legal texts into a deterministic graph representation (DACL) for adjudication, achieving near-perfect consistency and over 90% reduction in compute costs compared to runtime LRMs like GPT-5.2 and Gemini 3 Pro.
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.