KR Labs

About Us

KR Labs develops transparent and trustworthy AI solutions for natural language processing (NLP) applications. Founded by NLP researchers Ádám Kovács and Gábor Recski, with AI business leader Ashish Roy, the company bridges academic innovation with enterprise needs. Our products are designed to empower AI application developers, organizations, and individual users. We build open-source technology that combines novel statistical and rule-based methods, originally developed at TUW-NLP and HLT-Budapest. From 2023 to 2024, KR Labs was incubated at the TU Wien Innovation Incubation Center (i²c).

Our Products

LettuceDetect

LettuceDetect is a hallucination detection framework designed for Retrieval-Augmented Generation (RAG) systems. Built on ModernBERT, it identifies unsupported segments in LLM-generated answers in real time. It overcomes the limitations of short context windows and the high computational costs associated with large LLM-based detectors.

Token-Level Detection: Flags unsupported parts of answers.
Long-Context Support: Processes up to 4K tokens.
High Throughput: 30–60 examples per second on a single GPU.
Open Source: Released under the MIT License.

Learn More on GitHub • Download on PyPI • View Models on Hugging Face

VerbatimRAG

Traditional RAG systems retrieve relevant documents and then allow an LLM to freely generate responses based on that context. This can lead to hallucinations where the model invents facts not present in the source material. VerbatimRAG is our RAG framework that prevents hallucination by ensuring all generated content is explicitly derived from source documents.

Minimalistic: We provide a minimalistc end-to-end RAG system and many additional functionalities that you can integrate into your own solution.
How it works: We use extractive models to mark the relevant parts of the context and then implement dynamic template generation that is used to generate the final response.
Open Source: Released under the MIT License.

Learn More on GitHub

Contact Us

Email: info@krlabs.eu