Diversity Enhances an LLM's Performance in RAG and Long-context Task
This work addresses the challenge of improving LLM performance in RAG and long-context tasks by reducing redundancy, which is incremental as it builds on existing principles like MMR and FPS.
The paper tackles the problem of context window limitations in large language models (LLMs) for tasks like retrieval-augmented generation (RAG) and long-context summarization, where traditional similarity-based content selection leads to redundancy. By integrating diversity into content selection based on Maximal Marginal Relevance and Farthest Point Sampling, it shows that this approach substantially increases recall for selecting relevant sentences or chunks.
The rapid advancements in large language models (LLMs) have highlighted the challenge of context window limitations, primarily due to the quadratic time complexity of the self-attention mechanism (\(O(N^2)\), where \(N\) denotes the context window length). This constraint impacts tasks such as retrieval-augmented generation (RAG) in question answering (Q\&A) and long context summarization. A common approach involves selecting content with the highest similarity to the query; however, this often leads to redundancy and the exclusion of diverse yet relevant information. Building on principles from Maximal Marginal Relevance (MMR) and Farthest Point Sampling (FPS), we integrate diversity into the content selection process. Our findings reveal that incorporating diversity substantially increases the recall of selecting relevant sentences or chunks before LLM-based Q\&A and summarization. These results highlight the importance of maintaining diversity in future LLM applications to further improve summarization and Q\&A outcomes.