MétaCan
Menu
Back to cohort
Record W7106612763 · doi:10.1016/j.procs.2025.10.207

Multi-label classification of evolving psychosocial concerns using prompt-based large language models

2025· article· en· W7106612763 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

VenueProcedia Computer Science · 2025
Typearticle
Languageen
FieldPsychology
TopicMental Health via Writing
Canadian institutionsInstitut National de la Recherche ScientifiqueUniversité du Québec à Rimouski
Fundersnot available
KeywordsSubcategoryTask (project management)Language modelPsychosocialLanguage understanding

Abstract

fetched live from OpenAlex

Classifying short, evolving textual descriptions of psychosocial concerns presents major challenges for traditional machine learning (ML) and deep learning (DL) models, which often struggle to adapt to emerging or overlapping categories. Multi-label classification further complicates the task, requiring flexible mechanisms capable of assigning multiple relevant labels to a single input. This study introduces a local, prompt-based classification approach that reframes the task as text generation, enabling dynamic and hierarchical labeling without retraining. The system leverages open-source large language models (LLaMA 3.1, LLaMA 3.3, Mistral, and Qwen) to associate each concern with one or more categories while generating contextual explanations to support professional interpretation. LLaMA 3.1 achieved the highest accuracy (97.2%) at the subcategory level, outperforming both classical baselines and other 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.

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)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.981
Threshold uncertainty score0.569

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0010.000
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 head0.111
GPT teacher head0.437
Teacher spread0.326 · 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