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
Statewave use case in TypeScript: a grounded product advisor and support assistant, with an Ops Assistant that tracks and closes content gaps.
An open-source LLM for food product development
Lightweight open‑source RAG framework with claim‑level deterministic verifier — reducing hallucinations by refusing claims that lack evidence, not just generating them.
Turn research PDFs into grounded Markdown drafts — driven by any token-free AI coding-agent session (Claude, Codex, Gemini, Copilot, Cursor, Amp, Crush, Goose, Grok) when online, local Ollama when offline.
Deterministic multi-LLM orchestration with grounded, verified answers, an editable guardrail gate, and a live process dashboard.
Financial report grounded QA post-training with QLoRA SFT, DPO preference learning, citation/numeric evaluation, and badcase analysis.
本地企业多模态 Agent：精简Planner、LangGraph有限编排、SQL与混合检索、任务上下文与预算感知、轻量审核、可追溯多模态证据；附100题评测设计（迭代中）
HEFEST: on-prem рабочее место по химической безопасности завода: паспорта ГОСТ 30333, аварийные карточки, зоны АХОВ, совместимость хранения, СИЗ, класс отхода. Поиск тут фундамент, а не продукт. Офлайн, с провенансом, без выдуманной нормативки. | On-prem chemical safety for industrial plants, with provenance.
Levi's RAG is an AI due diligence copilot for equity research on Levi Strauss & Co. It answers natural-language financial questions using only official SEC filings, grounding each answer in the exact source sentence and tagging it with an evidence tier (verified, qualitative, benchmark, or inference).
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.
Conversational + predictive crime intelligence on Zoho Catalyst: ask 1M+ FIRs in English or Kannada and see the query and rows behind every answer. All-India NCRB-calibrated corpus (640 districts), forecasting validated on 6.37M real incidents, and a trilingual WhatsApp channel for field officers.
ComfyUI Custom Nodes for Gen Searcher and other tools
Developer-first prompt engineering patterns for grounded, testable, and reliable AI outputs.
Open-source ZenGrowth mirror: a local-first, verification-first career agent with auditable scoring, evidence-constrained materials, and human-controlled outbound actions
Secure Enterprise RAG platform with RBAC enforcement, OWASP LLM defenses, hybrid retrieval, grounded generation, explainability, and zero-trust context pipelines.
AI legal workspace with zero-hallucination case law research (grounded via live CourtListener queries), Claude-powered contract analysis with risk scoring, clause comparison, template-based drafting with clear AI/user provenance, and compliance checking. Built with Next.js and Claude 3.5 Sonnet.
Dependency-free checks for structured local-model output, grounded answers, citations, and protected writes.
To associate your repository with the grounded-generation topic, visit your repo's landing page and select "manage topics."