dragon-multiturn-context-encoder

Papers using or citing this model 2

• How to Train Your DRAGON: Diverse Augmentation Towards Generalizable Dense Retrieval 181 citations · 2023 · arXiv (Cornell University) · arXiv

  Various techniques have been developed in recent years to improve dense retrieval (DR), such as unsupervised contrastive learning and pseudo-query generation. Existing DRs, however, often suffer from effectiveness tradeoffs between...

• ChatQA: Surpassing GPT-4 on Conversational QA and RAG 121 citations · 2024 · arXiv (Cornell University) · arXiv

  In this work, we introduce ChatQA, a suite of models that outperform GPT-4 on retrieval-augmented generation (RAG) and conversational question answering (QA). To enhance generation, we propose a two-stage instruction tuning method that...