MétaCan
Menu
Back to cohort

Measuring the Knowledge Acquisition-Utilization Gap in Pretrained Language Models

2023· article· en· W4389518966 on OpenAlexaff
Amirhossein Kazemnejad, Mehdi Rezagholizadeh, Prasanna Parthasarathi, Sarath Chandar

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicTopic Modeling
Canadian institutionsPolytechnique MontréalMila - Quebec Artificial Intelligence InstituteCanadian Institute for Advanced ResearchMcGill University
Fundersnot available
KeywordsComputer scienceUSableDomain knowledgeRobustness (evolution)Parametric statisticsTask (project management)Measure (data warehouse)Knowledge acquisitionArtificial intelligenceKnowledge extractionMachine learningData miningEngineeringMathematics

Abstract

fetched live from OpenAlex

While pre-trained language models (PLMs) have shown evidence of acquiring vast amounts of knowledge, it remains unclear how much of this parametric knowledge is actually usable in performing downstream tasks.We propose a systematic framework to measure parametric knowledge utilization in PLMs.Our framework first extracts knowledge from a PLM's parameters and subsequently constructs a downstream task around this extracted knowledge.Performance on this task thus depends exclusively on utilizing the model's possessed knowledge, avoiding confounding factors like insufficient signal.Employing this framework, we study factual knowledge of PLMs and measure utilization across 125M to 13B parameter PLMs.We observe that: (1) PLMs exhibit two gaps -in acquired vs. utilized knowledge, (2) they show limited robustness in utilizing knowledge under distribution shifts, and (3) larger models close the acquired knowledge gap but the utilized knowledge gap remains.

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)0.010
metaresearch head score (Gemma)0.069
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Bench or experimental · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.010
Threshold uncertainty score0.054

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0100.069
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0020.001
Science and technology studies0.0010.001
Scholarly communication0.0030.008
Open science0.0010.004
Research integrity0.0020.003
Insufficient payload (model declined to judge)0.0020.001

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 head0.121
GPT teacher head0.301
Teacher spread0.180 · 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.

The models applied no category: nothing in the taxonomy fit this work.
Study designBench or experimental
Domainnot available
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

Citations3
Published2023
Admission routes1
Has abstractyes

Explore more

Same topicTopic ModelingFrench-language works237,207