Paper · arXiv 2407.14482
ChatQA 2: Bridging the Gap to Proprietary LLMs in Long Context and RAG Capabilities
Peng Xu, Wei Ping, Xianchao Wu, Zihan Liu, Mohammad Shoeybi, Bryan Catanzaro
ChatQA 2, a Llama3-based model, extends the context window to 128K tokens and enhances RAG performance, achieving accuracy comparable to GPT-4-Turbo on long-context tasks and surpassing it on RAG benchmarks.
Abstract
In this work, we introduce ChatQA 2, a Llama3-based model designed to bridge the gap between open-access LLMs and leading proprietary models (e.g., GPT-4-Turbo) in long-context understanding and retrieval-augmented generation (RAG) capabilities. These two capabilities are essential for LLMs to process large volumes of information that cannot fit into a single prompt and are complementary to each other, depending on the downstream tasks and computational budgets. We present a detailed continued training recipe to extend the context window of Llama3-70B-base from 8K to 128K tokens, along with a three-stage instruction tuning process to enhance the model's instruction-following, RAG performance, and long-context understanding capabilities. Our results demonstrate that the Llama3-ChatQA-2-70B model achieves accuracy comparable to GPT-4-Turbo-2024-0409 on many long-context understanding tasks and surpasses it on the RAG benchmark. Interestingly, we find that the state-of-the-art long-context retriever can alleviate the top-k context fragmentation issue in RAG, further improving RAG-based results for long-context understanding tasks. We also provide extensive comparisons between RAG and long-context solutions using state-of-the-art long-context LLMs.