cs.LGMar 8, 2026

Deterministic Fuzzy Triage for Legal Compliance Classification and Evidence Retrieval

Authors: Rian Atri

Organizations: Serval Systems

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

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.

Figures & tables

MethodN@5N@10P4@5Q
Dual enc. ( w=0w{=}0 )0.4220.4960.37157
Dual enc. ( w=200w{=}200 )0.3780.4520.37157
Table 1: ACORD retrieval: NDCG@5 (N@5), NDCG@10 (N@10), and 4-star precision@5 (P4@5) over QQ queries. “Dual enc.” denotes the dual encoder with fuzzy head.
MethodPrecRecF1
Majority (all neg.)0.0000.0000.000
Random0.0060.5040.013
Dual enc. ( w=0w{=}0 )0.2560.2000.224
Dual enc. ( w=200w{=}200 )0.1740.9750.295
Table 2: CUAD binary classification performance: precision (Prec), recall (Rec), F1, area under ROC (AUC), and accuracy (Acc). “Dual enc.” denotes the dual encoder with fuzzy head.
More in this topic

Legal NLP

Legal natural language processing (NLP) develops methods for analyzing and generating statutes, cases, contracts, and legal advice.

See all 109 papers

Explore similar work

CardsList
Apr 20, 2026

LegalBench-BR: A Benchmark for Evaluating Large Language Models on Brazilian Legal Decision Classification

We introduce LegalBench-BR, the first public benchmark for evaluating language models on Brazilian legal text classification. The dataset comprises 3,105 appellate proceedings from the Santa Catarina State Court (TJSC), collected via the DataJud API (CNJ) and annotated across five legal areas through LLM-assisted labeling with heuristic validation. On a class-balanced test set, BERTimbau-LoRA, updating only 0.3% of model parameters, achieves 87.6% accuracy and 0.87 macro-F1 (+22pp over Claude 3.5 Haiku, +28pp over GPT-4o mini). The gap is most striking on administrativo (administrative law): GPT-4o mini scores F1 = 0.00 and Claude 3.5 Haiku scores F1 = 0.08 on this class, while the fine-tuned model reaches F1 = 0.91. Both commercial LLMs exhibit a systematic bias toward civel (civil law), absorbing ambiguous classes rather than discriminating them, a failure mode that domain-adapted fine-tuning eliminates. These results demonstrate that general-purpose LLMs cannot substitute for domain-adapted models in Brazilian legal classification, even when the task is a simple 5-class problem, and that LoRA fine-tuning on a consumer GPU closes the gap at zero marginal inference cost. We release the full dataset, model, and pipeline to enable reproducible research in Portuguese legal NLP.

Pedro Barbosa de Carvalho Neto

Teresina, PI, Brazil

Legal NLPLLM EvaluationText ClassificationLanguage Model Bias EvaluationClassification
AskPDF
Mar 26, 2026

Can Small Models Reason About Legal Documents? A Comparative Study

Large language models show promise for legal applications, but deploying frontier models raises concerns about cost, latency, and data privacy. We evaluate whether sub-10B parameter models can serve as practical alternatives by testing nine models across three legal benchmarks (ContractNLI, CaseHOLD, and ECtHR) using five prompting strategies (direct, chain-of-thought, few-shot, BM25 RAG, and dense RAG). Across 405 experiments with three random seeds per configuration, we find that a Mixture-of-Experts model activating only 3B parameters matches GPT-4o-mini in mean accuracy while surpassing it on legal holding identification, and that architecture and training quality matter more than raw parameter count. Our largest model (9B parameters) performs worst overall. Chain-of-thought prompting proves sharply task-dependent, improving contract entailment but degrading multiple-choice legal reasoning, while few-shot prompting emerges as the most consistently effective strategy. Comparing BM25 and dense retrieval for RAG, we find near-identical results, suggesting the bottleneck lies in the language model's utilization of retrieved context rather than retrieval quality. All experiments were conducted via cloud inference APIs at a total cost of $62, demonstrating that rigorous LLM evaluation is accessible without dedicated GPU infrastructure.

Snehit Vaddi

Independent Researcher

Small Language ModelsLegal ReasoningLLM EvaluationLegal Document AnalysisLLM PromptingRetrieval-Augmented Generation
AskPDF
May 16, 2026

Retrieval-Based Multi-Label Legal Annotation: Extensible, Data-Efficient and Hallucination-Free

Multi-label legal annotation requires assigning multiple labels from large, evolving taxonomies to long, fact-intensive documents, often under limited supervision. Parametric encoders typically require task-specific training and retraining when the label set changes, while prompting generative large language models becomes costly and degrades as the label space grows. We cast legal annotation as retrieval: we embed documents and label descriptions with a frozen retrieval model and predict labels via k-nearest neighbors in the embedding space, enabling updates by re-embedding and re-indexing rather than gradient-based backpropagation. Across three legal datasets (ECtHR-A, ECtHR-B, and Eurlex with 100 labels), retrieval achieves competitive accuracy and strong data efficiency; on Eurlex, Qwen-8B retrieval improves Macro-F1 from 40.41 (GPT-5.2, zero-shot) to 49.12 while reducing estimated compute by 20-30 times compared to fine-tuning. With only (N=100) training samples, retrieval nearly doubles Micro-F1 over hierarchical Legal-BERT on ECtHR-A (48.29 vs. 27.87). We also quantify a reliability failure mode of generative inference: GPT-5.2 hallucinates labels outside the provided taxonomy in 0.12-0.9% of test samples under deterministic decoding. In contrast, retrieval strictly respects defined label sets, eliminating hallucination by design. These results suggest retrieval-model-based annotators are a practical, deployable alternative for high-cardinality and rapidly changing legal label spaces.

Li Zhang, Jaromir Savelka, Kevin Ashley

University of Pittsburgh, Pittsburgh, PA, USA · Carnegie Mellon University, Pittsburgh, PA, USA

Legal NLPMulti-Label ClassificationRetrieval-Augmented ClassificationLegal Document Analysis
AskPDF