Pith. sign in

REVIEW 8 cited by

Dynamic Parametric Retrieval Augmented Generation for Test-time Knowledge Enhancement

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2503.23895 v4 pith:HKF27CVJ submitted 2025-03-31 cs.CL cs.AI

Yuqiao Tan , Shizhu He , Huanxuan Liao , Jun Zhao , Kang Liu This is my paper · ORCID
classification cs.CLcs.AI
keywords knowledgeparametricllmscostsdypragtest-timeinferencetraining
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Retrieval-augmented generation (RAG) enhances large language models (LLMs) by retrieving relevant documents from external sources and incorporating them into the context. While it improves reliability by providing factual texts, it significantly increases inference costs as context length grows and introduces challenging issue of RAG hallucination, primarily caused by the lack of corresponding parametric knowledge in LLMs. An efficient solution is to enhance the knowledge of LLMs at test-time. Parametric RAG (PRAG) addresses this by embedding document into LLMs parameters to perform test-time knowledge enhancement, effectively reducing inference costs through offline training. However, its high training and storage costs, along with limited generalization ability, significantly restrict its practical adoption. To address these challenges, we propose Dynamic Parametric RAG (DyPRAG), a novel framework that leverages a lightweight parameter translator model to efficiently convert documents into parametric knowledge. DyPRAG not only reduces inference, training, and storage costs but also dynamically generates parametric knowledge, seamlessly enhancing the knowledge of LLMs and resolving knowledge conflicts in a plug-and-play manner at test-time. Extensive experiments on multiple datasets demonstrate the effectiveness and generalization capabilities of DyPRAG, offering a powerful and practical RAG paradigm which enables superior knowledge fusion and mitigates RAG hallucination in real-world applications. Our code is available at https://github.com/Trae1ounG/DyPRAG.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. RWGBench: Evaluating Scholarly Positioning in Related Work Generation

    cs.DL 2026-05 unverdicted novelty 7.0 of 10

    RWGBench measures related-work generation by citation choices, and shows citation-focused metrics expose failures that text-similarity and LLM-judge scores miss.

  2. FedMosaic: Federated Retrieval-Augmented Generation via Parametric Adapters

    cs.CL 2026-02 conditional novelty 6.0 of 10

    FedMosaic is a federated RAG system that encodes local documents as mask-gated LoRA adapters, clusters related documents into shared adapters, and selectively merges only relevant, low-conflict adapters at the server.

  3. MHA-RAG: Improving Efficiency, Accuracy, and Consistency by Encoding Exemplars as Soft Prompts

    cs.AI 2025-10 conditional novelty 6.0 of 10

    MHA-RAG encodes retrieved exemplars into order-invariant soft prompts via multi-head attention, claiming ~20-point effective-accuracy gains over RAG at ~10x lower inference FLOPs.

  4. EraRAG: Efficient and Incremental Retrieval Augmented Generation for Growing Corpora

    cs.IR 2025-06 conditional novelty 6.0 of 10

    EraRAG uses hyperplane-based locality-sensitive hashing to build a hierarchical retrieval graph whose affected regions only are re-summarized when new documents arrive, cutting update cost by up to an order of magnitude.

  5. GRIP: In-Parameter Graph Reasoning through Fine-Tuning Large Language Models

    cs.CL 2025-11 reject novelty 5.0 of 10

    An LLM can memorize a knowledge graph into LoRA weights and answer relation/reasoning queries about it without graph context, but the evaluation partly trains on the test task.

  6. MemOS: An Operating System for Memory-Augmented Generation (MAG) in Large Language Models

    cs.CL 2025-05 reject novelty 4.0 of 10

    A unified memory-operating-system design for LLMs, built around a MemCube abstraction, is presented without any experimental validation.

  7. Neural Incompatibility: The Unbridgeable Gap of Cross-Scale Parametric Knowledge Transfer in Large Language Models

    cs.CL 2025-05 conditional novelty 4.0 of 10

    Directly transferring parameters between differently-sized language models is unreliable; the paper proposes a pre-alignment method (LaTen) and explains the failure via 'Neural Incompatibility'.

  8. Dynamic and Parametric Retrieval-Augmented Generation

    cs.CL 2025-06 unverdicted novelty 2.0 of 10

    A tutorial outline that categorizes recent RAG work into Dynamic RAG and Parametric RAG, and explains why both are needed.

Pith tools