cuad

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

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.

Benchmark zero-shot LLM vs fine-tuned transformers for contract clause classification on the CUAD dataset: precision, recall, F1, cost & latency side by side.

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

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

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

Turns contract PDFs into structured records where every extracted value carries a verbatim quote from the source - anything it can't quote is reported missing, not guessed. Docling + LangGraph, evaluated on CUAD.