CogDoc

Read full text Summarise with VIRAT
Authors: Abdul Anees, Sreeja Alle, Veerababu Reddy, Purna Chandu Repana, Pravallika Bhosale, Sri Vardhini Nidamanuri
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

πŸ“œ CogDoc LLM: Privacy-Preserving Document Intelligence CogDoc is an offline, privacy-first legal and policy document analysis system. It utilizes a multi-model pipeline to segment clauses, detect contradictions (NLI), and provide AI-driven risk assessments without sending data to the cloud. πŸš€ Features Offline Execution: Runs entirely on local hardware for data sovereignty. Multi-Model Pipeline: * Mistral-7B (GGUF): For high-level reasoning and risk assessment. DeBERTa-v3-small: For Natural Language Inference (NLI) and clause cross-checking. spaCy: For high-speed document segmentation. Interactive Dashboard: Built with React and FastAPI. πŸ“Š Datasets This project utilizes multiple benchmark datasets for legal and policy document analysis. These datasets cover tasks such as clause classification, contract understanding, legal entailment, and summarization. πŸ”Ή LEDGAR A large-scale dataset for contract clause classification derived from SEC filings. πŸ”— https://github.com/IBM/ledgar πŸ”Ή CUAD (Contract Understanding Atticus Dataset) A benchmark dataset for extracting and classifying important clauses in legal contracts. πŸ”— https://github.com/TheAtticusProject/cuad πŸ”Ή ContractNLI A natural language inference dataset for legal contracts, enabling reasoning over contractual clauses. πŸ”— https://stanfordnlp.github.io/contract-nli/ πŸ”Ή BillSum A dataset for summarization of U.S. Congressional and California state bills. πŸ”— https://github.com/FiscalNote/BillSum πŸ”Ή ILDC (Indian Legal Documents Corpus) A dataset focused on Indian legal case documents for classification and judgment prediction tasks. πŸ”— https://github.com/Legal-NLP-EkStep/ILDC ⚠️ Usage Note All datasets are publicly available. Please refer to the respective repositories for licensing terms, access conditions, and citation requirements. πŸ“Œ Citation If you use these datasets, please cite the original sources as specified in their respective repositories. πŸ› οΈ Setup & Installation 1. Clone the Repository PowerShell git clone cd legal-ai-app/app 2. Create and Activate Virtual Environment It is recommended to use a dedicated virtual environment to avoid dependency conflicts. PowerShell # Create the environment python -m venv backend-venv # Activate it (Windows) .\backend-venv\Scripts\activate 3. Install Requirements Install the core dependencies and fix the numpy version for compatibility with spaCy. PowerShell pip install -r requirements.txt pip install "numpy

Fields of Study & Subjects

Artificial Intelligence in Law Topic Modeling Handwritten Text Recognition Techniques

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
26 March 2026
Language
EN