Large-scale pretrained models for goal-directed dialog

Open-vocabulary Object Segmentation with Diffusion Models

This is a list of open-source projects at Microsoft Research NLP Group

Financial report grounded QA post-training with QLoRA SFT, DPO preference learning, citation/numeric evaluation, and badcase analysis.

Beginner-friendly Python RAG project that turns StackOverflow Q&A data into a grounded knowledge assistant using sentence-transformer embeddings, FAISS retrieval, and strict citation-based LLM answering.

Developer-first prompt engineering patterns for grounded, testable, and reliable AI outputs.

Secure Enterprise RAG platform with RBAC enforcement, OWASP LLM defenses, hybrid retrieval, grounded generation, explainability, and zero-trust context pipelines.

URIM is a local grounded chat runtime for querying boxed authority content with a fixed, deterministic retrieval pipeline.

A grounded answer engine demonstrating Brave Search's Web Search vs LLM Context endpoints — Next.js 15 + Vercel AI SDK + Claude

Adaptive quiz generation from PDFs using interpretable NLP, grounded LLMs, and deep knowledge tracing.

Anchored {{key | value}} placeholders for hallucination-safe LLM generation in finance.

Production-oriented local RAG system with FAISS, FastAPI, and Docker, featuring confidence-gated generation, safe refusals, and grounded citations. Built with real-world reliability and deployment in mind.

Personal RAG avatar agent that answers in my voice using a private, continuously evolving knowledge base with grounded retrieval.

RAG system for Trine University international students. Provides grounded answers on admissions, CPT/OPT, scholarships, insurance using 10 FAQ documents. Built with Python, ChromaDB, Groq LLM, and Gradio UI

Grounded RAG v1 specification with abstain/partial semantics

KG-based Text World Models & Semantic Dynamics for Conversational AI — build, simulate, and reason over a user's semantic world with text-native graphs and time-aware rules.

ComfyUI Custom Nodes for Gen Searcher and other tools

一个面向职业内容检索与证据化总结的 AI Native Web 应用，支持混合检索、引用和证据片段展示。

Vectara — RAG-as-a-service platform with grounded generation

Answer ultra-precise questions about any open-source project from its real source code, issues, PRs, docs and the web — grounded retrieval, not the model's memory. A skills.sh agent skill + zero-dependency CLI.