MétaCan
Menu
Back to cohort

Unsupervised Key-Value Pair selection on Enterprise Documents through Generative type Transformer Framework

2025· article· W7147479603 on OpenAlexaff
Hemasree Koganti, Vasanthi Jangala Naga, Viyyapu Pushpa, Savita P Vibhute, Mohit Tiwari, Keerthana N V

Bibliographic record

Venuenot available
Typearticle
Language
FieldComputer Science
TopicAdvanced Text Analysis Techniques
Canadian institutionsArtificial Intelligence in Medicine (Canada)
Fundersnot available
KeywordsGenerative grammarTransformerUnsupervised learningAutomationGenerative modelGeneralization

Abstract

fetched live from OpenAlex

The research system being proposed is a key-value pair extraction model that uses an unsupervised approach for enterprise documents while enhancing the capabilities of Generative Pretrained Transformer (GPT) systems. Unlike traditional rule-based or supervised methods that require significant amounts of labelled data, the system is capable of automatically identifying and organising key-value relationships in various types of documents without any prior guidance. The main goal is to combine a generative language model that is capable of understanding with unsupervised learning methods to capture semantic relationships and contextual dependencies for the accurate mapping of values to the corresponding keys. Moreover, the proposed model implements an adaptive fine-tuning strategy for generalization across different enterprise-based domains, thus improving its system applicability in large-scale document processing scenarios. Besides controlling information, this model also limits the manual intervention that could be made, thereby paving the way for the smartness of enterprise automation form and an efficient knowledge management system.

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 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 categoriesMeta-epidemiology (narrow)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Theoretical or conceptual · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.534
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0000.004
Science and technology studies0.0010.000
Scholarly communication0.0010.002
Open science0.0010.000
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0010.000

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 head0.014
GPT teacher head0.324
Teacher spread0.310 · 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 teacher head, not a consensus.

Study designTheoretical or conceptual
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 topicAdvanced Text Analysis TechniquesFrench-language works237,207