BEE-RAG: Balanced Entropy Engineering for Retrieval-Augmented Generation
This addresses a bottleneck in RAG systems for enhancing large language models, though it appears incremental as it builds on existing RAG approaches.
The paper tackles the problem of performance degradation in retrieval-augmented generation (RAG) due to long context lengths, which cause unconstrained entropy growth and attention dilution, and proposes the BEE-RAG framework that improves adaptability through entropy invariance, achieving effectiveness in experiments across multiple RAG tasks.
With the rapid advancement of large language models (LLMs), retrieval-augmented generation (RAG) has emerged as a critical approach to supplement the inherent knowledge limitations of LLMs. However, due to the typically large volume of retrieved information, RAG tends to operate with long context lengths. From the perspective of entropy engineering, we identify unconstrained entropy growth and attention dilution due to long retrieval context as significant factors affecting RAG performance. In this paper, we propose the balanced entropy-engineered RAG (BEE-RAG) framework, which improves the adaptability of RAG systems to varying context lengths through the principle of entropy invariance. By leveraging balanced context entropy to reformulate attention dynamics, BEE-RAG separates attention sensitivity from context length, ensuring a stable entropy level. Building upon this, we introduce a zero-shot inference strategy for multi-importance estimation and a parameter-efficient adaptive fine-tuning mechanism to obtain the optimal balancing factor for different settings. Extensive experiments across multiple RAG tasks demonstrate the effectiveness of BEE-RAG.