Scaling Legal AI: Benchmarking Mamba and Transformers for Statutory Classification and Case Law Retrieval

Anuraj Maurya

cs.CYAug 29, 2025

Scaling Legal AI: Benchmarking Mamba and Transformers for Statutory Classification and Case Law Retrieval

Authors: Anuraj Maurya

Organizations: Bengaluru, India

Abstract

Statutory corpora and judicial decisions are growing faster than legal professionals can read them, while individual judgments often exceed the context limits of standard encoder models. Transformer architectures dominate legal NLP benchmarks, but their quadratic attention complexity can require truncating or fragmenting documents that demand whole-document reasoning. Selective state-space models (SSMs), such as Mamba, offer linear-time sequence modeling and are a promising alternative for long legal documents, yet their performance on legal classification and retrieval remains underexplored. We present a preliminary benchmark comparing Mamba and SSD-Mamba with BERT, DeBERTa, and Longformer across four legal classification tasks (ECtHR, EUR-Lex, SCOTUS, and ILDC/ILC) and two case-retrieval tasks (ECtHR and ILDC), using a shared windowing and aggregation pipeline. The strongest SSM performs within approximately 1.3 percentage points of the strongest transformer across tasks and metrics. SSD-Mamba achieves the best results on most metrics for ECtHR classification, ILDC classification, and ECtHR retrieval, while processing approximately 3 times more tokens per second than DeBERTa and 4 times more than Longformer. DeBERTa remains strongest on SCOTUS and EUR-Lex F1. These results are preliminary because they do not include variance estimates across random seeds or statistical significance testing. Rather than presenting a definitive ranking, we use these findings to motivate further evaluation with repeated-seed experiments, statistical testing, and controls for model capacity and computational efficiency.

Explore similar work

Apr 20, 2026cs.CL

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 Domain Legal Natural Language Processing Benchmarks Natural Language Processing Automatic Labelling

Ask PDF

Apr 20, 2026cs.CL

Towards Intelligent Legal Document Analysis: CNN-Driven Classification of Case Law Texts

Legal practitioners and judicial institutions face an ever-growing volume of case-law documents characterised by formalised language, lengthy sentence structures, and highly specialised terminology, making manual triage both time-consuming and error-prone. This work presents a lightweight yet high-accuracy framework for citation-treatment classification that pairs lemmatisation-based preprocessing with subword-aware FastText embeddings and a multi-kernel one-dimensional Convolutional Neural Network (CNN). Evaluated on a publicly available corpus of 25,000 annotated legal documents with a 75/25 training-test partition, the proposed system achieves 97.26% classification accuracy and a macro F1-score of 96.82%, surpassing established baselines including fine-tuned BERT, Long Short-Term Memory (LSTM) with FastText, CNN with random embeddings, and a Term Frequency-Inverse Document Frequency (TF-IDF) k-Nearest Neighbour (KNN) classifier. The model also attains the highest Area Under the Receiver Operating Characteristic (AUC-ROC) curve of 97.83% among all compared systems while operating with only 5.1 million parameters and an inference latency of 0.31 ms per document - more than 13 times faster than BERT. Ablation experiments confirm the individual contribution of each pipeline component, and the confusion matrix reveals that residual errors are confined to semantically adjacent citation categories. These findings indicate that carefully designed convolutional architectures represent a scalable, resource-efficient alternative to heavyweight transformers for intelligent legal document analysis.

Moinul Hossain, Sourav Rabi Das, Zikrul Shariar Ayon +4

Department of Computer Science and Engineering, American International University–Bangladesh, Dhaka 1229, Bangladesh · Department of Computer Science and Engineering, Prime University, Dhaka, Bangladesh · Department of Mechanical Engineering, Shajalal University of Science and Technology, Sylhet, Bangladesh +2

Large Language Model Classification Term Frequency-Inverse Document Frequency Document Citations Token Embeddings

Ask PDF

May 27, 2026cs.CL

UA-Legal-Bench: A Benchmark for Evaluating Large Language Models on Ukrainian Legal Reasoning

Legal NLP benchmarks are overwhelmingly English-centric, leaving failure modes in morphologically rich, non-Latin-script languages undetected. We introduce UA-Legal-Bench, a five-task benchmark for evaluating large language models on Ukrainian legal reasoning, built from the Unified State Register of Court Decisions (EDRSR) -- one of the world's largest open judicial corpora (99.5 million decisions). The benchmark comprises: (1) case-type classification (4 classes, n=2,000), (2) judgment form classification (4 classes, n=2,000), (3) case-outcome prediction (6 classes, n=800), (4) legal norm extraction (n=1,794), and (5) cause category prediction (22 classes, n=1,871). We evaluate 11 LLMs (3B--675B) from five families under zero-shot and 3-shot prompting via AWS Bedrock with 158K API calls. Our results reveal sharply task-dependent few-shot effects: few-shot prompting improves judgment form classification by up to +38.6 pp but has mixed effects on outcome prediction. We show that accuracy is misleading on imbalanced legal tasks: the model with highest COP accuracy (62%) is a majority-class predictor (macro-F1: 23%), while the genuinely best model scores only 44% macro-F1. Within-family scaling analysis reveals that 8B models can match frontier performance on surface-level tasks but scaling thresholds vary dramatically across families. We release all data, prompts, and model predictions.

Volodymyr Ovcharov

SecondLayer

Legal Reasoning Tasks Legal Natural Language Processing Benchmarks Ukrainian Judgement Text Corpora Few-Shot Learning

Ask PDF