REVIEW 7 cited by
Parametric Retrieval Augmented Generation
Not yet reviewed by Pith; the record is open.
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
read the original abstract
Retrieval-augmented generation (RAG) techniques have emerged as a promising solution to enhance the reliability of large language models (LLMs) by addressing issues like hallucinations, outdated knowledge, and domain adaptation. In particular, existing RAG methods append relevant documents retrieved from external corpus or databases to the input of LLMs to guide their generation process, which we refer to as the in-context knowledge injection method. While this approach is simple and often effective, it has inherent limitations. Firstly, increasing the context length and number of relevant documents can lead to higher computational overhead and degraded performance, especially in complex reasoning tasks. More importantly, in-context knowledge injection operates primarily at the input level, but LLMs store their internal knowledge in their parameters. This gap fundamentally limits the capacity of in-context methods. To this end, we introduce Parametric retrieval-augmented generation (Parametric RAG), a new RAG paradigm that integrates external knowledge directly into the parameters of feed-forward networks (FFN) of an LLM through document parameterization. This approach not only saves online computational costs by eliminating the need to inject multiple documents into the LLMs' input context, but also deepens the integration of external knowledge into the parametric knowledge space of the LLM. Experimental results demonstrate that Parametric RAG substantially enhances both the effectiveness and efficiency of knowledge augmentation in LLMs. Also, it can be combined with in-context RAG methods to achieve even better performance. We have open-sourced all the code, data, and models in the following anonymized GitHub link: https://github.com/oneal2000/PRAG
Forward citations
Cited by 7 Pith papers
-
Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories
Sleep-time Knowledge Seeding plus Dreaming lets LLMs expand capacity, distill fragile in-context memories into stable parameters, and self-improve without human labels.
-
AI5GTest: AI-Driven Specification-Aware Automated Testing and Validation of 5G O-RAN Components
An LLM-based framework that generates expected O-RAN and 3GPP procedural flows from standards and validates captured signaling logs against them, reporting 100% accuracy on 15 testbed instances and under an hour per t...
-
Cartridges: Lightweight and general-purpose long context representations via self-study
A per-corpus trained KV cache, called a Cartridge, matches full-context in-context learning quality on long-document benchmarks while using up to 38.6x less serving memory.
-
GRIP: In-Parameter Graph Reasoning through Fine-Tuning Large Language Models
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.
-
LoRA-Augmented Generation (LAG) for Knowledge-Intensive Language Tasks
LAG is a two-stage router that filters a 1,000-adapter LoRA library with Arrow and reranks with SpectR, outperforming the Arrow baseline and reaching 92.1% of its Oracle's performance on KILT tasks.
-
MemOS: An Operating System for Memory-Augmented Generation (MAG) in Large Language Models
A unified memory-operating-system design for LLMs, built around a MemCube abstraction, is presented without any experimental validation.
-
Dynamic and Parametric Retrieval-Augmented Generation
A tutorial outline that categorizes recent RAG work into Dynamic RAG and Parametric RAG, and explains why both are needed.
Discussion (0). Continue with ORCID to comment.