MétaCan
Menu
Back to cohort
Record W4412571954 · doi:10.3390/electronics14152922

Towards Reliable and Efficient Natural Language Processing in Emergent Technologies

2025· article· en· W4412571954 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.
fundA Canadian funder is recorded on the work.

Bibliographic record

VenueElectronics · 2025
Typearticle
Languageen
FieldEngineering
TopicRobotics and Automated Systems
Canadian institutionsUniversité du Québec à Montréal
FundersSocial Sciences and Humanities Research Council of Canada
KeywordsComputer scienceNatural (archaeology)Natural language processingArtificial intelligenceGeographyArchaeology

Abstract

fetched live from OpenAlex

LLMs have created new possibilities for machines to learn from data and produce content without human intervention. We address the question of whether they provide reliable and efficient Natural Language Processing. We differentiate Generative Grammar Language Models from Large Language Models. We take Structure Dependency to be a first principle of language, a prerequisite to Semantic Compositionality, applying in conjunction with Principles of Efficient Computation to generate structured content. We discuss the behavior of ChatGPT-3.5, GPT-4.o mini and Grok 3 in response to complex queries including pronominal Binding, Coreference, and structural ambiguity and point to the relevance of deep syntactic and semantic principles for LLMs. We outline consequences for the development of reliable and efficient Natural Language Processing systems in emergent technologies.

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)0.000
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: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.477
Threshold uncertainty score0.285

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
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 head0.003
GPT teacher head0.216
Teacher spread0.214 · 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