Rajarshi Roy
Rajarshi Roy has 2 papers in our library, in 2024, most of them on Language models & pretraining, Question answering, Dialogue systems; often with Bryan Catanzaro, Chankyu Lee, Mohammad Shoeybi.
No OpenAlex profile matched yet.
📄 2 works in our library · 🔗 Cited 260 times in our library · ⭐ Paper Stars ranking: #5107
Fields, topics and concepts
📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Arts and Humanities · 2 worksComputer Science · 2 worksArtificial Intelligence · 2 worksComputer Vision and Pattern Recognition · 2 worksLanguage and Linguistics · 2 worksInformation Systems · 1 work
🧭 Topics 3Research subjects and languages the work is about.Language models & pretraining · 2 worksDialogue systems · 1 workQuestion answering · 1 work
Works by year
2020s
Papers
- NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models (2024 · 222 citations)
General-purpose text embeddings are used for search, clustering, classification and the retrieval step in RAG systems. - ChatQA: Surpassing GPT-4 on Conversational QA and RAG (2024 · 58 citations)
The paper asks whether open-weight LLMs can match proprietary systems like GPT-4 at answering multi-turn questions grounded in supplied or retrieved documents, including tables, arithmetic, and questions the context cannot answer.
Co-authors here
Venues
Cited by
Updated
This page in Markdown → https://md.research.elamur.ai/free/en/authors/rajarshi-roy/