MétaCan
Menu
← Back to cohort

GPTViet: An Open-Source Vietnamese Foundation Model from Pretraining to Domain Specialization

2025· article· W7127321268 on OpenAlexaff
Thang Nguyen-Truong, Nhiem Tran, Ngoc Truong, Thanh Le-Hoang, Kien Bui-De, Dong Tran-Manh

Bibliographic record

Venuenot available
Typearticle
Language
FieldMedicine
TopicArtificial Intelligence in Healthcare and Education
Canadian institutionsAlpha Technologies (Canada)
Fundersnot available
KeywordsVietnameseDomain (mathematical analysis)Foundation (evidence)Work (physics)Domain-specific languageLanguage model

Abstract

fetched live from OpenAlex

As open-source Large Language Models (LLMs) increasingly rival proprietary counterparts, the need for foundational models tailored to specific linguistic and cultural contexts becomes critical. This paper presents GPTViet, a series of foundational LLMs for the Vietnamese language. Built upon the LLaMA architecture, GPTViet was developed by curating a high-quality Vietnamese corpus and performing extensive finetuning on a range of model sizes (8 B to 70 B parameters). Evaluations demonstrate that GPTViet models significantly outperform their respective base models on Vietnamese-specific tasks, as measured by standard benchmarks and our custombuilt VietExam benchmark. The practical utility of this work is showcased through domain-specific application, VietHealth 70B for medical consultation. Adhering to the principles of open source Llama, GPTViet and all its derivatives are publicly released under an open-source license. This initiative provides the Vietnamese research and development community with a powerful, adaptable foundation to accelerate the creation of diverse intelligent applications. For more information, please visit https://github.com/VietnamAIHub/GPTViet and demo at http://gptviet.ioit.ac.vn/.

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)0.001
metaresearch head score (Gemma)0.004
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: Empirical · Consensus signal: none
Teacher disagreement score0.020
Threshold uncertainty score0.047

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0010.004
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0000.001
Bibliometrics0.0010.001
Science and technology studies0.0000.000
Scholarly communication0.0010.002
Open science0.0020.002
Research integrity0.0010.002
Insufficient payload (model declined to judge)0.0140.006

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 head0.196
GPT teacher head0.475
Teacher spread0.279 · 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
GenreEmpirical

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 topicArtificial Intelligence in Healthcare and Education→French-language works237,207→