cuad

AI-powered contract review skill with CUAD risk detection, market benchmarks, and lawyer-ready redlines. Works with Claude Code, Codex, Cursor, and 26+ tools.

Benchmark Microsoft Foundry Content Understanding on CUAD legal contracts. Achieves 83.3% F1 score (29% better than GPT-4o baseline). Complete Python notebook with optimized schemas for contract clause extraction. Production-ready with confidence scores & cost analysis.

Pre-embedding definition injection for legal contract RAG — fixes the Definition Dependency Gap in CUAD contracts. Code and benchmark for the DAPEI paper.

Document Q&A with verifiable citations over CUAD contracts: BM25 retrieval, local LLM via Ollama, grounded quotes, abstention and evaluation

AI contract review: clause extraction with code-verified quotes, YAML playbook risk flags and cited Q&A. FastAPI + LangGraph + Claude, evaluated on CUAD v1.

Contract review assistant on CUAD: fine-tuned DeBERTa vs a local LLM, with verbatim quotes and a risk playbook

Verification-gated redlining for SaaS contracts: clause extraction, a 12-rule risk playbook and an evidence gate before any redline, benchmarked on 510 CUAD contracts.

Evaluation of Llama 3.2 3B on CUAD Dataset - before and after finetuning

Multi-agent LLM-based contract review system — Summer School Turco 2026

Check contracts for clauses on an ordinary PC with a small local model (Jeff). Measured on 102 lawyer-labelled contracts.

Clause risk analysis for Indian commercial contracts, with span-grounded findings, calibrated abstention and Indian case law evidence

AI contract analysis: clause extraction, risk flagging, and cited Q&A — honestly evaluated against lawyer annotations (CUAD)

End-to-end Agentic RAG system for legal contract analysis — hybrid retrieval (BM25 + dense + RRF), cross-encoder reranking, LangGraph agent with 3 tools, LLM-as-a-judge evaluation, FastAPI + Streamlit + Docker Compose. Built on CUAD (406 contracts, 22K expert annotations). Zero cost — all free-tier tools.

RAG contratual avaliado pelo que recusa responder: 510 contratos e 20.910 perguntas (CUAD).

Professional commercial contract search platform powered by Qdrant vector search and the CUAD dataset. Features 510 real contracts with 13K+ expert-labeled clauses, semantic search, and coarse-to-fine retrieval pipelines.

AI-powered contract intelligence & risk engine with open-vocabulary clause classification, interactive systemic risk graphs, and real-time What-If redline simulations.

Multi-label classification of commercial contract clauses into six risk-relevant categories, on CUAD v1- 510 contracts annotated by lawyers at The Atticus Project.

QLoRA fine-tuning of Qwen2.5-7B on CUAD legal contracts with a rigorous before/after eval: clause classification 61.5%→80%, missed clauses 57%→5%, calibration error 10× lower, hallucinations hand-audited (1.0%→3.5%). Trained on a free T4, runs on a 6 GB GPU, with a FastAPI + Streamlit demo.

LoRA fine-tune of Qwen2.5-1.5B (4-bit, MLX) for exact contract clause extraction on CUAD. Test F1 0.664 -> 0.924, hallucination 21.7% -> 0.0%.

QLoRA fine-tune of Qwen3-4B on CUAD — 41 clause types, verbatim extraction, evaluated against zero-shot frontier models