This work presents PROSLEX (PRediction Of Statutes and LEgal eXplanation), a comprehensive dataset comprising 1,623 expert-annotated legal documents from the Indian context, positioning PROSLEX as a benchmark for developing explainable AI systems that can support legal practitioners while advancing research in interpretable legal NLP.
Abstract
Legal Statute Prediction (LSP) involves automatically identifying relevant legal statutes given factual descriptions in legal documents, typically framed as a multi-label classification task within natural language processing and information retrieval research. While recent advances have begun incorporating Large Language Models (LLMs) for statute prediction, current approaches primarily focus on accuracy metrics without addressing the critical need for legal reasoning, a fundamental requirement in judicial contexts where decisions must be explainable and justifiable. To address this research gap, we present PROSLEX (PRediction Of Statutes and LEgal eXplanation), a comprehensive dataset comprising 1,623 expert-annotated legal documents from the Indian context. Each document is paired with statute predictions and detailed explanations, totaling 7,450 explanations, capturing the underlying legal reasoning. Using this dataset, we systematically evaluate various prompting strategies, including zero-shot, few-shot, chain-of-thought, and tree-of-thoughts approaches, to generate both statute predictions and their corresponding legal rationales. Our evaluation framework measures not only predictive performance but also the coherence and legal validity of generated explanations, positioning PROSLEX as a benchmark for developing explainable AI systems that can support legal practitioners while advancing research in interpretable legal NLP. To ensure reproducibility, we have made our PROSLEX dataset and model code available on GitHub: https://github.com/subinay494/Legal_Statute_Prediction_Explanation.
This paper introduces the task of identifying and segmenting legal conditions (Tatbestand) and legal consequences (Rechtsfolge) within German statutory texts and presents ANNOTARES (Annotations of Tatbestand-Rechtsfolge Sequences), a novel dataset comprising German law texts with span-level annotations.
With more than 45 million cases awaiting disposal across Indian courts as of 2024, the judicial system faces an acute
need for faster, smarter tools to support legal research. This work introduces an artificial-intelligence-driven legal research
assistant tailored to the jurisprudence of the Supreme Court of India. Starting from a case description written in ordinary
language, the system executes a four-stage pipeline: first, it performs dense semantic search by encoding the 26,688 judgments
of the Indian Legal Documents Corpus (ILDC) with InLegalBERT and indexing roughly 1.1 million resulting text segments
through a FAISS IVFFlat structure; second, it applies cross-encoder reranking to narrow the retrieved candidates down to the
five precedents judged most semantically relevant; third, it forecasts the judicial outcome across three possible categories—
Allowed, Dismissed, or Partly Allowed—via an InLegalBERT classification head paired with SHAP explainability; and fourth, it
produces a structured reasoning summary in Issue–Rule–Application–Conclusion (IRAC) form using the Llama 3 8B model
served locally through Ollama. By combining semantic search, neural reranking, interpretable outcome prediction, and AIgenerated legal reasoning inside one coherent architecture, the framework helps legal practitioners locate relevant precedents,
anticipate probable case outcomes, and streamline the overall research process. Constructed entirely from openly accessible
Indian legal resources and transformer-based architectures, the system establishes an extensible base for intelligent legal
support within the Indian judiciary
Krish P. Gokhale, Tanvi Kshirsagar, Anugraha Kasbe et al.· International Journal for Re...· 0 citations
Juris Policy Optimization (JPO), a post-training framework for structured legal reasoning in Chinese criminal judgment prediction, is proposed and experiments show that JPO consistently improves both judgment prediction and reasoning quality over supervised fine-tuning and reinforcement learning baselines.
Zhao-Lu Kang, Yan-Tao Liu, Tailong Luo et al.· 1 citation
This work proposes LexKairos, a comprehensive benchmark for evaluating the temporal capabilities of LLMs in the Chinese legal context across three dimensions: statutory temporal knowledge, case temporal modeling, and statute-case temporal reasoning.
Chenyang Li, Ze-Jia Feng, Yuqi Huang et al.· 0 citations
We identify and quantify temporal misgrounding: the systematic retrieval and citation of the currently in-force version of a legal article when the applicable version is an earlier or future one. Standard legal RAG treats the corpus as static; we argue legal question answering is a temporally-indexed retrieval problem. We introduce FiscalQA Pro, pairing a versioned corpus of 32,436 article-versions of the French tax code (93 years, 1938-2031) with an all-model-hard temporal-reasoning track: 209 scored, expert-reviewed questions across 33 CGI articles (221 released; twelve flagged out of the answerable scope). At selection time, no evaluated model recovered its date-applicable answer closed-book in any of four sampling draws, and the currently in-force text lacks the gold value for all but one of the scored questions. Answers are scored deterministically via atomic ground-truth"nuggets"(regex and numeric-with-tolerance), never LLM-as-judge: an LLM judge would inherit the temporal bias it is meant to score. Across eleven models (five frontier closed-API systems plus Gemini 2.5 Pro as a substitute entry, and five open-weight), parametric knowledge yields 3.0% mean strict accuracy and RAG over a static current-version corpus 2.7%. Static RAG retrieves the date-applicable version 0% of the time, confidently citing a real but inapplicable version. Our end-to-end retriever over a multi-version index, with no oracle, reaches 98.3% mean strict; an oracle-article ablation reaches 99.1%, locating the residual gap in first-stage recall, not version selection. We additionally release a version-aware jurisprudence dataset of 69,208 citation links, together with the corpus, benchmark, model responses, and pipeline code.
This paper outlines a unique method of legal text processing using Natural Language Processing (NLP) technology to extract the information from the legal texts meaningfully and naturally. The proposed system is designed in a data pipeline architecture by integrating the NLP functionalities such as tokenization, part-of-speech tagging, named entity recognition (NER), and dependency parsing to systematize the processing of typologies of legal text hubs, including legal briefs, statutes, and case law. The methodology presented concerns the importance of pre-processing legal texts that address domain-specific challenges. The texts may contain ambiguities, while the legal language itself is a very intricate kind of language. The system uses advanced methods like syntactic parsing and semantic role labeling to parse and find relevant entities, relationships, and context, ensuring the automation of the large amount of raw legal data for review and analysis. Besides that, the first is leveraging machine learning models to optimize the data extraction process and to ensure high efficiency and scalability. This methodology guarantees that accurate and reliable information is extracted and reduces the time and costs that conventionally come with manual legal analysis. The focal point of the offered system is overcoming legal workflow issues and bringing model texts to widespread use. Therefore, the proposed system aims to facilitate decision-making processes in legal practice and even the accuracy of the proposed model.
S. A. Gade, Sivaram Ponnusamy· Journal of Intelligent Decis...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
