MétaCan
Menu
Back to cohort
Record W7126381417 · doi:10.21428/594757db.3f69a234

Advancements in Large Language Models Through Employment of Retrieval Augmented Generation and its Enhancements for Assistance in Academia

2025· article· en· W7126381417 on OpenAlexaff
Naheen Kabir

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicTopic Modeling
Canadian institutionsUniversity of Calgary
Fundersnot available
KeywordsPopularityDomain (mathematical analysis)Language modelData modelingTopic model

Abstract

fetched live from OpenAlex

Recent surge in popularity of Large Language Models (LLMs) has contributed to greater interest in research for making them highly efficient and improving accuracy of responses generated. Retrieval Augmented Generation is a model proposed that can be integrated into most LLMs to assist with domain specific applications by making responses align accurately with user prompts. An area that could greatly benefit from usage of RAG is academia, where a major part is dependent on retrieving research papers and documents relevant to the researcher’s proposed thesis and can become time consuming in the long run. This paper will survey proposed advancements in LLMs with the use of RAGs as well as selected refinements to the RAG model that would increase both efficiency and accuracy of document retrieval and response generation. We then propose a novel system to make use of LLM equipped with RAG to be used for retrieval of research documents relevant to a researcher’s topic and areas of interest, ensuring texts are relevant to the source.

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 imitation

Not 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.

metaresearch head score (Codex)0.009
metaresearch head score (Gemma)0.024
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Bench or experimental · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.009
Threshold uncertainty score0.050

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0090.024
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.002
Bibliometrics0.0020.001
Science and technology studies0.0010.001
Scholarly communication0.0030.006
Open science0.0020.003
Research integrity0.0020.003
Insufficient payload (model declined to judge)0.0080.008

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 head0.041
GPT teacher head0.342
Teacher spread0.301 · 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

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designBench or experimental
Domainnot available
GenreMethods

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".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same topicTopic ModelingFrench-language works237,207