Generation-Augmented Generation: A Plug-and-Play Framework for Private Knowledge Injection in Large Language Models

• URL: http://arxiv.org/abs/2601.08209v1
• Date: Tue, 13 Jan 2026 04:23:36 GMT
• Title: Generation-Augmented Generation: A Plug-and-Play Framework for Private Knowledge Injection in Large Language Models
• Authors: Rongji Li, Jian Xu, Xueqing Chen, Yisheng Yang, Jiayi Wang, Xingyu Chen, Chunyu Xie, Dawei Leng, Xu-Yao Zhang,
• Abstract summary: Generation-Augmented Generation (GAG) treats private expertise as an additional expert modality and injects it via a compact representation-level interface.<n>GAG improves specialist performance over strong RAG baselines by 15.34% and 14.86% on two benchmarks.
• Score: 48.65910216527897
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In domains such as biomedicine, materials, and finance, high-stakes deployment of large language models (LLMs) requires injecting private, domain-specific knowledge that is proprietary, fast-evolving, and under-represented in public pretraining. However, the two dominant paradigms for private knowledge injection each have pronounced drawbacks: fine-tuning is expensive to iterate, and continual updates risk catastrophic forgetting and general-capability regression; retrieval-augmented generation (RAG) keeps the base model intact but is brittle in specialized private corpora due to chunk-induced evidence fragmentation, retrieval drift, and long-context pressure that yields query-dependent prompt inflation. Inspired by how multimodal LLMs align heterogeneous modalities into a shared semantic space, we propose Generation-Augmented Generation (GAG), which treats private expertise as an additional expert modality and injects it via a compact, representation-level interface aligned to the frozen base model, avoiding prompt-time evidence serialization while enabling plug-and-play specialization and scalable multi-domain composition with reliable selective activation. Across two private scientific QA benchmarks (immunology adjuvant and catalytic materials) and mixed-domain evaluations, GAG improves specialist performance over strong RAG baselines by 15.34% and 14.86% on the two benchmarks, respectively, while maintaining performance on six open general benchmarks and enabling near-oracle selective activation for scalable multi-domain deployment.

Related papers

• Differentially Private Retrieval-Augmented Generation [13.622078883013442]
  Retrieval-augmented generation (RAG) is a widely used framework for reducing hallucinations in large language models (LLMs)<n>RAG poses serious privacy risks when the database contains sensitive corpora, such as medical records or legal documents.<n>We present DP-KSA, a novel privacy-preserving RAG algorithm that integrates DP using the propose-test-release paradigm.
  arXiv  Detail & Related papers  (2026-02-16T00:52:57Z)
• Evontree: Ontology Rule-Guided Self-Evolution of Large Language Models [12.36467850170776]
  Evontree is a novel framework that leverages a small set of high-quality rules to extract, validate, and enhance domain knowledge within large language models (LLMs)<n>Experiments on medical QA benchmarks with Llama3-8B-Instruct and Med42-v2 demonstrate consistent outperformance over both unmodified models and leading supervised baselines.
  arXiv  Detail & Related papers  (2025-10-30T16:53:45Z)
• Domain-Specific Data Generation Framework for RAG Adaptation [58.20906914537952]
  Retrieval-Augmented Generation (RAG) combines the language understanding and reasoning power of large language models with external retrieval to enable domain-grounded responses.<n>We propose RAGen, a framework for generating domain-grounded question-answer-context (QAC) triples tailored to diverse RAG adaptation approaches.
  arXiv  Detail & Related papers  (2025-10-13T09:59:49Z)
• What Makes You Unique? Attribute Prompt Composition for Object Re-Identification [70.67907354506278]
  Object Re-IDentification aims to recognize individuals across non-overlapping camera views.<n>Single-domain models tend to overfit to domain-specific features, whereas cross-domain models often rely on diverse normalization strategies.<n>We propose an Attribute Prompt Composition framework, which exploits textual semantics to jointly enhance discrimination and generalization.
  arXiv  Detail & Related papers  (2025-09-23T07:03:08Z)
• Fine-Grained Privacy Extraction from Retrieval-Augmented Generation Systems via Knowledge Asymmetry Exploitation [15.985529058573912]
  Retrieval-augmented generation (RAG) systems enhance large language models (LLMs) by integrating external knowledge bases.<n>Existing privacy attacks on RAG systems can trigger data leakage but often fail to accurately isolate knowledge-base-derived sentences within mixed responses.<n>This paper presents a novel black-box attack framework that exploits knowledge asymmetry between RAG and standard LLMs to achieve fine-grained privacy extraction.
  arXiv  Detail & Related papers  (2025-07-31T03:50:16Z)
• Detecting and Pruning Prominent but Detrimental Neurons in Large Language Models [68.57424628540907]
  Large language models (LLMs) often develop learned mechanisms specialized to specific datasets.<n>We introduce a fine-tuning approach designed to enhance generalization by identifying and pruning neurons associated with dataset-specific mechanisms.<n>Our method employs Integrated Gradients to quantify each neuron's influence on high-confidence predictions, pinpointing those that disproportionately contribute to dataset-specific performance.
  arXiv  Detail & Related papers  (2025-07-12T08:10:10Z)
• MetaGen Blended RAG: Unlocking Zero-Shot Precision for Specialized Domain Question-Answering [0.0]
  We introduce 'MetaGen Blended RAG', a novel enterprise search approach that enhances semantic retrievers.<n>By leveraging key concepts, topics, and acronyms, our method creates metadata-enriched semantic indexes and boosted hybrid queries.<n>On the biomedical PubMedQA dataset, MetaGen Blended RAG achieves 82% retrieval accuracy and 77% RAG accuracy, surpassing all prior zero-shot RAG benchmarks.
  arXiv  Detail & Related papers  (2025-05-23T17:18:45Z)
• UniversalRAG: Retrieval-Augmented Generation over Corpora of Diverse Modalities and Granularities [53.76854299076118]
  UniversalRAG is a novel RAG framework designed to retrieve and integrate knowledge from heterogeneous sources with diverse modalities and granularities.<n>We propose a modality-aware routing mechanism that dynamically identifies the most appropriate modality-specific corpus and performs targeted retrieval within it.<n>We validate UniversalRAG on 8 benchmarks spanning multiple modalities, showing its superiority over various modality-specific and unified baselines.
  arXiv  Detail & Related papers  (2025-04-29T13:18:58Z)
• Generate, Discriminate, Evolve: Enhancing Context Faithfulness via Fine-Grained Sentence-Level Self-Evolution [61.80716438091887]
  GenDiE (Generate, Discriminate, Evolve) is a novel self-evolving framework that enhances context faithfulness through fine-grained sentence-level optimization.<n>By treating each sentence in a response as an independent optimization unit, GenDiE effectively addresses the limitations of previous approaches.<n>Experiments on ASQA (in-domain LFQA) and ConFiQA datasets demonstrate that GenDiE surpasses various baselines in both faithfulness and correctness.
  arXiv  Detail & Related papers  (2025-03-03T16:08:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.