A Hybrid Retrieval-Augmented Generation and Language Model Framework for Evidence-Grounded Review Systems
Bibliographic record
Abstract
Evidence-grounded review systems require balancing comprehensive knowledge retrieval with accurate and reliable generation. Traditional approaches often struggle with maintaining factual consistency, providing proper attribution, and combining complex multi-source evidence. In this study we propose a reliable hybrid framework that integrates retrieval-augmented generation with large language models to support evidence-grounded critiques, risk assessments, and recommendations. The framework created ensures to incorporate structured rubrics, a dual-model verification, and a human-in-the-loop to enforce and ensure quality control to produce reliable outputs across domains. Unlike prior systems such as Atlas and RETRO, the approach proposed in this research introduces explicit verification and calibration mechanisms that reduce factual errors and improve attribution. Empirical evaluations applied show visible and notable improvements in groundedness (91% vs. 71% baseline), consistency (89% vs. 63% baseline), and reliability (ECE 0.042, 47% lower than Atlas). Our approach uses a browser-based architecture which removes the need for specialised hardware, making the system more accessible. This work advances the development of trustworthy review systems and has broader implications for high-stakes fields such as healthcare, legal analysis, and policy evaluation.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.039 | 0.113 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.003 |
| Bibliometrics | 0.005 | 0.003 |
| Science and technology studies | 0.001 | 0.003 |
| Scholarly communication | 0.007 | 0.006 |
| Open science | 0.004 | 0.007 |
| Research integrity | 0.003 | 0.003 |
| Insufficient payload (model declined to judge) | 0.007 | 0.003 |
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 source (direct Gemma or distilled Codex), 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".