MétaCan
Menu
Back to cohort
Record W4391464262 · doi:10.1162/qss_a_00285

Large-scale text analysis using generative language models: A case study in discovering public value expressions in AI patents

2024· article· en· W4391464262 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.

fundA Canadian funder is recorded on the work.
no affNo Canadian affiliation: this work is invisible to an affiliation-only frame.
No Canadian affiliation. An affiliation-only frame, the usual design, would never have seen this work. It is one of the works that make the case for inverting the frame.

Bibliographic record

VenueQuantitative Science Studies · 2024
Typearticle
Languageen
FieldSocial Sciences
TopicComputational and Text Analysis Methods
Canadian institutionsnot available
FundersSocial Sciences and Humanities Research Council of CanadaBiotechnology and Biological Sciences Research CouncilDirectorate for Biological SciencesSnap
KeywordsGenerative grammarNatural language processingScale (ratio)Value (mathematics)Computer scienceGenerative modelArtificial intelligenceLinguisticsMachine learningGeographyCartographyPhilosophy

Abstract

fetched live from OpenAlex

Abstract We put forward a novel approach using a generative language model (GPT-4) to produce labels and rationales for large-scale text analysis. The approach is used to discover public value expressions in patents. Using text (5.4 million sentences) for 154,934 US AI patent documents from the United States Patent and Trademark Office (USPTO), we design a semi-automated, human-supervised framework for identifying and labeling public value expressions in these sentences. A GPT-4 prompt is developed that includes definitions, guidelines, examples, and rationales for text classification. We evaluate the labels and rationales produced by GPT-4 using BLEU scores and topic modeling, finding that they are accurate, diverse, and faithful. GPT-4 achieved an advanced recognition of public value expressions from our framework, which it also uses to discover unseen public value expressions. The GPT-produced labels are used to train BERT-based classifiers and predict sentences on the entire database, achieving high F1 scores for the 3-class (0.85) and 2-class classification (0.91) tasks. We discuss the implications of our approach for conducting large-scale text analyses with complex and abstract concepts. With careful framework design and interactive human oversight, we suggest that generative language models can offer significant assistance in producing labels and rationales.

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)0.005
metaresearch head score (Gemma)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Qualitative · Consensus signal: Qualitative
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.324
Threshold uncertainty score0.997

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0050.001
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0020.011
Science and technology studies0.0010.001
Scholarly communication0.0000.002
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 head0.255
GPT teacher head0.524
Teacher spread0.268 · 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