Bibliographic record
Abstract
Retrieval-augmented generation (RAG) is a hybrid architecture that combines the generative power of large language models (LLMs) with the factual reliability of information retrieval systems. Although the emergence of large language models (LLMs) has significantly improved the performance of natural language understanding and generation tasks. However, these models often suffer from information distortion, outdated information, and lack of transparency. Retrieval-augmented generation (RAG) addresses these limitations by introducing an external retrieval mechanism into the generation process. RAG systems follow the retrieve first, then generate paradigm, which retrieves relevant documents from knowledge sources and uses them as input to the language model. This approach enables the model to generate more accurate, solid, and timely responses. RAG has become an infrastructure for knowledge-intensive natural language processing (NLP) and LLM. In this review, we comprehensively review the basic architecture of RAG systems, analyze key components such as retrievers and generators, compare mainstream implementations, and evaluate their performance on various tasks. We also discuss challenges in the RAG pipeline, including latency, hallucinations, context filtering, and knowledge freshness. Finally, we highlight future research directions in terms of scalability, personalization, and integration with structured knowledge sources.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.002 | 0.004 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".