MétaCan
Menu
Back to cohort
Record W4402996633 · doi:10.1177/10497315241280686

Moving Beyond ChatGPT: Local Large Language Models (LLMs) and the Secure Analysis of Confidential Unstructured Text Data in Social Work Research

2024· article· en· W4402996633 on OpenAlexaff
Brian E. Perron, Hui Luan, Bryan G. Victor, Oliver Hiltz-Perron, Joseph P. Ryan

Bibliographic record

VenueResearch on Social Work Practice · 2024
Typearticle
Languageen
FieldPsychology
TopicMental Health via Writing
Canadian institutionsQueen's University
Fundersnot available
KeywordsConfidentialityComputer scienceUnstructured dataComputer securityData scienceInternet privacyInformation extractionServerWelfareArtificial intelligenceBig dataData miningWorld Wide WebPolitical scienceLaw

Abstract

fetched live from OpenAlex

Purpose: Large language models (LLMs) have demonstrated remarkable abilities in natural language tasks. However, their use in social work research is limited by confidentiality and security concerns when processing sensitive data. This study addresses these challenges by evaluating the performance of local LLMs (LocalLLMs) in classifying and extracting substance-related problems from unstructured child welfare investigation summaries. LocalLLMs allow researchers to analyze data on their own computers without transmitting information to external servers for processing. Methods: Four state-of-the-art LocalLLMs—Mistral-7b, Mixtral-8 × 7b, LLama3-8b, and Llama3-70b—were tested using zero-shot prompting on 2,956 manually coded summaries. Results: The LocalLLMs achieved exceptional results comparable to human experts in classification and extraction, demonstrating their potential to unlock valuable insights from confidential, unstructured child welfare data. Conclusions: This study highlights the feasibility of using LocalLLMs to efficiently analyze large amounts of textual data while addressing the confidentiality issues associated with proprietary LLMs.

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)0.014
metaresearch head score (Gemma)0.046
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesMetaresearch
Consensus categoriesnone
DomainCandidate signal: Methods · Consensus signal: none
Study designCandidate signal: Theoretical or conceptual · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.986
Threshold uncertainty score0.073

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0140.046
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0020.001
Science and technology studies0.0010.001
Scholarly communication0.0030.007
Open science0.0010.004
Research integrity0.0010.003
Insufficient payload (model declined to judge)0.0030.002

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 head0.551
Teacher spread0.376 · 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.

Study designTheoretical or conceptual
DomainMethods
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

Citations19
Published2024
Admission routes1
Has abstractyes

Explore more

Same venueResearch on Social Work PracticeSame topicMental Health via WritingFrench-language works237,207