Lune

ACL Findings2026

NeuRAG: End-to-End Neural Knowledge Augmentation via Hyper-Neurons

Liwei Zheng, Xuemin Liu, Jie Liu

Abstract

Retrieval-Augmented Generation (RAG) systems have become a standard approach for grounding large language models in external knowledge. However, they are constrained by a decoupled architecture: retrieval and reasoning operate as separate stages, with retrieved text merely prepended as passive context. This prevents deep integration of knowledge into the model's parametric reasoning, leading to fragmented responses for complex queries requiring multi-document synthesis or conflict resolution. To bridge this gap, we propose NeuRAG, an end-to-end Neuralized RAG framework that unifies knowledge retrieval and fusion through Hyper-Neurons-parameterized modules encoding entire documents directly into the model's parameter space, framing retrieval as dynamic reconfiguration of the model's parameter space rather than static context augmentation. In NeuRAG, each document is encoded as a lightweight LoRA module, conceptualized as a knowledge neuron. These neurons collectively form a document-adaptive Hyper-Layer, which dynamically activates and fuses knowledge neurons via an attention mechanism conditioned on the input hidden-state query. This enables the model to jointly retrieve and reason within a single forward pass, seamlessly integrating external knowledge into its inference pathway. Extensive experiments across multiple datasets and LLMs demonstrate NeuRAG's strong and consistent performance as a promising novel RAG paradigm.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection cites Active Retrieval Augmented Generation
  • Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection cites Retrieval Augmented Language Model Pre-Training
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on9

  1. Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
  2. Retrieval Augmented Language Model Pre-TrainingKelvin Guu, Kenton Lee, Zora Tung, Panupong Pasupat et al.ICML 2020 · 2,937 citations
  3. Self-RAG: Learning to Retrieve, Generate, and Critique through Self-ReflectionAkari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil et al.ICLR 2024 · 1,798 citations
  4. M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge DistillationJianlyu Chen, Shitao Xiao, Peitian Zhang, Kun Luo et al.ACL Findings 2024 · 762 citations
  5. Active Retrieval Augmented GenerationZhengbao Jiang, Frank F. Xu, Luyu Gao, Zhiqing Sun et al.EMNLP 2023 · 315 citations

Related papers

  1. RAG+: Enhancing Retrieval-Augmented Generation with Application-Aware ReasoningYu Wang, Shiwan Zhao, Zhihu Wang, Ming Fan et al.EMNLP 2025 · 3 citations
  2. Query-Aware Knowledge Retrieval via Hyperbolic StructuringChuang Zhou, Junnan Dong, Yilin Xiao, Shengyuan Chen et al.ACL 2026
  3. RouteRAG: Efficient Retrieval-Augmented Generation from Text and Graph via Reinforcement LearningYucan Guo, Miao Su, Saiping Guan, Zihao Sun et al.ACL Findings 2026 · 2 citations
  4. StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information StructurizationZhuoqun Li, Xuanang Chen, Haiyang Yu, Hongyu Lin et al.ICLR 2025
  5. Parametric Retrieval Augmented GenerationWeihang Su, Yichen Tang, Qingyao Ai, Junxi Yan et al.SIGIR 2025 · 25 citations
Dusk over the sea between two cliffs drawn in fine vertical lines