Marina Danilevsky
Senior Research Scientist and manager at IBM Research; co-author of the MTRAG multi-turn RAG benchmark
- Senior Research Scientist, Manager - core language and conversational technologies, IBM Research1
Marina Danilevsky is a Senior Research Scientist and Manager for core language and conversational technologies at IBM Research, working on generative language models, evaluation, and human-in-the-loop approaches. Danilevsky is the last author of MTRAG, a human-generated benchmark of multi-turn retrieval-augmented generation conversations whose data and corpora IBM publishes in an Apache-2.0 repository, and a co-author of the follow-up MTRAG-UN benchmark. Danilevsky is also among the authors of Label Sleuth, an open-source no-code system for labeling text and building text classifiers.1234
Work
MTRAG (Multi-Turn RAG Benchmark) (external site: github.com)Open data
Last author of "MTRAG: A Multi-Turn Conversational Benchmark for Evaluating Retrieval-Augmented Generation Systems" (2025) and co-author of MTRAG-UN (2026); the IBM/mt-rag-benchmark repository, under the Apache-2.0 license, provides the human and synthetic conversation data and document corpora.23
Label Sleuth (external site: arxiv.org)Published research
Listed among the authors of "Label Sleuth: From Unlabeled Text to a Classifier in a Few Hours" (2022), which introduces a free, open-source, no-code system for labeling text and creating text classifiers.4
This profile covers public professional work only, from the sources below. It is not an endorsement or a ranking. To correct or remove it, use the correction form.