LGMar 8

Deterministic Fuzzy Triage for Legal Compliance Classification and Evidence Retrieval

arXiv:2603.07390v1
Predicted impact top 98% in LG · last 90 daysOriginality Incremental advance
AI Analysis

This work provides a more transparent and reproducible machine learning approach for legal teams to triage contractual evidence, addressing concerns about model opacity and non-determinism in sensitive legal contexts.

This paper proposes a deterministic dual encoder system with fuzzy triage bands for legal compliance classification and evidence retrieval. It achieves NDCG@5 0.38-0.42 and NDCG@10 0.45-0.50 on ACORD-style retrieval, and AUC 0.98-0.99 and F1 0.22-0.30 on CUAD-derived binary compliance, outperforming baselines in a highly imbalanced setting.

Legal teams increasingly use machine learning to triage large volumes of contractual evidence, but many models are opaque, non-deterministic, and difficult to align with frameworks such as HIPAA or NERC-CIP. We study a simple, reproducible alternative based on deterministic dual encoders and transparent fuzzy triage bands. We train a RoBERTa-base dual encoder with a 512-dimensional projection and cosine similarity on the ACORD benchmark for graded clause retrieval, then fine-tune it on a CUAD-derived binary compliance dataset. Across five random seeds (40-44) on a single NVIDIA A100 GPU, the model achieves ACORD-style retrieval performance of NDCG@5 0.38-0.42, NDCG@10 0.45-0.50, and 4-star Precision@5 about 0.37 on the test split. On CUAD-derived binary labels, it achieves AUC 0.98-0.99 and F1 0.22-0.30 depending on positive-class weighting, outperforming majority and random baselines in a highly imbalanced setting with a positive rate of about 0.6%. We then map scalar compliance scores into three regions: auto-noncompliant, auto-compliant, and human-review. Thresholds are tuned on validation data to maximize automatic decision coverage subject to an empirical error-rate constraint of at most 2% over auto-decided examples. The result is a seed-stable system summarized by a small number of scalar parameters. We argue that deterministic encoders, calibrated fuzzy bands, and explicit error constraints provide a practical middle ground between hand-crafted rules and opaque large language models, supporting explainable evidence triage, reproducible audit trails, and concrete mappings to legal review concepts.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes