BEE-RAG: Balanced Entropy Engineering for Retrieval-Augmented Generation

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Wang, Yuhao, Ren, Ruiyang, Wang, Yucheng, Liu, Jing, Zhao, Wayne Xin, Wu, Hua, Wang, Haifeng
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912697178652672
author Wang, Yuhao
Ren, Ruiyang
Wang, Yucheng
Liu, Jing
Zhao, Wayne Xin
Wu, Hua
Wang, Haifeng
author_facet Wang, Yuhao
Ren, Ruiyang
Wang, Yucheng
Liu, Jing
Zhao, Wayne Xin
Wu, Hua
Wang, Haifeng
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_05100
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle BEE-RAG: Balanced Entropy Engineering for Retrieval-Augmented Generation
Wang, Yuhao
Ren, Ruiyang
Wang, Yucheng
Liu, Jing
Zhao, Wayne Xin
Wu, Hua
Wang, Haifeng
Computation and Language
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.
title BEE-RAG: Balanced Entropy Engineering for Retrieval-Augmented Generation
topic Computation and Language
url https://arxiv.org/abs/2508.05100