AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

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

Yuhao Wang, Ruiyang Ren, Yucheng Wang, Jing Liu, Xin Zhao, Hua Wu, Haifeng Wang

AAAI 2026 · Large language models › Retrieval and knowledge · approach: RAG robustness and evaluation · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add balanced entropy factor β (ablation)Zero-BEE · Zero-shot, avg EM (Table 2)EM: 20.35 -> 31.42Improved
add mean µ of balancing factor (ablation)Zero-BEE · Zero-shot, avg EM (Table 2)EM: 27.47 -> 31.42Improved
add variance σ2 of balancing factor (ablation)Zero-BEE · Zero-shot, avg EM (Table 2)EM: 26.92 -> 31.42Improved
add parallel intrinsic multi-importance inference (ablation)Zero-BEE · Zero-shot, avg EM (Table 2)EM: 29.89 -> 31.42Improved
replace β with reranker scores (ablation)Zero-BEE · Zero-shot, avg EM (Table 2)EM: 31.42 -> 28.87Hurt
add residual in sentence-level vector (ablation)Light-BEE · Fine-tuning, avg EM (Table 2)EM: 23.65 -> 38.09Improved
add initialization constraint on β (ablation)Light-BEE · Fine-tuning, avg EM (Table 2)EM: 3.23 -> 38.09Improved
add FFN module (ablation)Light-BEE · Fine-tuning, avg EM (Table 2)EM: 38.09 -> 36.41Hurt
replace β with reranker scores (ablation)Light-BEE · Fine-tuning, avg EM (Table 2)EM: 38.09 -> 35.82Hurt
apply BEE zero-shot over vanilla RAGQwen-2.5-7B · Average of 4 QA datasetsEM: 28.65 -> 31.42Improved
apply Light-BEE over LoRAQwen-2.5-7B · Average of 4 QA datasetsEM: 33.70 -> 38.09Improved
prompt-based CoT / Chain-of-Note / Self-Critic over vanilla RAGQwen-2.5-7B · Average of 4 QA datasetsEM: 28.65 -> 28.89 (CoT)No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy