paper-with-me

홈 › Papers

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

2026-01-13 · Rongji Li, Jian Xu, Yi Chen, Xueqing Chen, Yisheng Yang, Jiayi Wang, Xingyu Chen, Chunyu Xie, Dawei Leng, Xu-Yao Zhang arxiv

In domains such as materials science, biomedicine, 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 clear drawbacks: fine-tuning is expensive to iterate under continual updates that can induce catastrophic forgetting and general-capability regression; retrieval-augmented generation (RAG) keeps the base model intact but remains brittle in specialized private corpora due to chunk-induced evidence fragmentation, retrieval mismatch, and long-context pressure. 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 auxiliary modality and injects it into a frozen base model through a compact, constant-budget latent interface. Concretely, GAG distills question-conditioned specialist knowledge from lightweight domain experts into multi-slot latent memories, integrates multi-layer expert signals via per-slot cross-layer fusion, and aligns them to the frozen base model through gated residual projection, while supporting scalable mixed-domain deployment with reliable selective activation. In a unified mixed-domain evaluation spanning two scientific private-domain QA benchmarks (catalytic materials and immunology adjuvant) together with general-domain queries, GAG consistently outperforms strong retrieval-based and parameter-efficient fine-tuning baselines on specialist QA, while preserving general-domain capability, achieving highly reliable routing, and offering a favorable efficiency--effectiveness trade-off. Code and datasets are provided in the supplementary material. Code is publicly available at https://github.com/360CVGroup/GAG.

📄 PDF Abstract BibTeX arXiv:2601.08209

Code (0)

등록된 구현이 없습니다.

Tasks

parameter-efficient fine-tuning

Similar Papers 제목 키워드 기반

BSharedRAG: Backbone Shared Retrieval-Augmented Generation for the E-commerce Domain

2024-09-30 · Kaisi Guan, Qian Cao, Yuchong Sun, Xiting Wang 외

Retrieval Augmented Generation (RAG) system is important in domains such as e-commerce, which has many long-tail entities and frequently updated information. Most existing works adopt separate modules for retrieval and g…

RAGRetrievalRetrieval-augmented Generation

Plan$\times$RAG: Planning-guided Retrieval Augmented Generation

2024-10-28 · Prakhar Verma, Sukruta Prakash Midigeshi, Gaurav Sinha, Arno Solin 외

We introduce Planning-guided Retrieval Augmented Generation (Plan$\times$RAG), a novel framework that augments the \emph{retrieve-then-reason} paradigm of existing RAG frameworks to \emph{plan-then-retrieve}. Plan$\times…

Answer GenerationRAGRetrievalRetrieval-augmented Generation

C-3PO: Compact Plug-and-Play Proxy Optimization to Achieve Human-like Retrieval-Augmented Generation

2025-02-10 · Guoxin Chen, Minpeng Liao, Peiying Yu, Dingmin Wang 외

Retrieval-augmented generation (RAG) systems face a fundamental challenge in aligning independently developed retrievers and large language models (LLMs). Existing approaches typically involve modifying either component …

RAGRetrievalRetrieval-augmented Generation

Plug and Play Counterfactual Text Generation for Model Robustness

2022-06-21 · Nishtha Madaan, Srikanta Bedathur, Diptikalyan Saha

Generating counterfactual test-cases is an important backbone for testing NLP models and making them as robust and reliable as traditional software. In generating the test-cases, a desired property is the ability to cont…

AttributecounterfactualText Generation

MoRAG -- Multi-Fusion Retrieval Augmented Generation for Human Motion

2024-09-18 · Sai Shashank Kalakonda, Shubh Maheshwari, Ravi Kiran Sarvadevabhatla

We introduce MoRAG, a novel multi-part fusion based retrieval-augmented generation strategy for text-based human motion generation. The method enhances motion diffusion models by leveraging additional knowledge obtained …

Motion GenerationRetrievalRetrieval-augmented Generation