Observations on Building RAG Systems for Technical Documents

التفاصيل البيبلوغرافية
العنوان: Observations on Building RAG Systems for Technical Documents
المؤلفون: Soman, Sumit, Roychowdhury, Sujoy
سنة النشر: 2024
المجموعة: Computer Science
مصطلحات موضوعية: Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Computer Science - Computation and Language, I.2.7
الوصف: Retrieval augmented generation (RAG) for technical documents creates challenges as embeddings do not often capture domain information. We review prior art for important factors affecting RAG and perform experiments to highlight best practices and potential challenges to build RAG systems for technical documents.
Comment: Published as a Tiny Paper at ICLR 2024
نوع الوثيقة: Working Paper
URL الوصول: http://arxiv.org/abs/2404.00657
رقم الأكسشن: edsarx.2404.00657
قاعدة البيانات: arXiv