MétaCan
Menu
Back to cohort

A Hybrid Retrieval-Augmented Generation and Language Model Framework for Evidence-Grounded Review Systems

2025· preprint· en· W4415009153 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

Venuenot available
Typepreprint
Languageen
FieldSocial Sciences
TopicComputational and Text Analysis Methods
Canadian institutionsArtificial Intelligence in Medicine (Canada)
Fundersnot available
KeywordsLanguage modelKey (lock)Modeling languageField (mathematics)Natural language

Abstract

fetched live from OpenAlex

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.

Full frame distilled prediction

Teacher imitation

Not 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.

metaresearch head score (Codex)0.003
metaresearch head score (Gemma)0.003
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Theoretical or conceptual · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.848
Threshold uncertainty score0.653

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0030.003
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

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.

Opus teacher head0.175
GPT teacher head0.468
Teacher spread0.293 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same topicComputational and Text Analysis MethodsFrench-language works237,207