MétaCan
Menu
Back to cohort
Record W4388555939 · doi:10.48550/arxiv.2311.04900

How Abstract Is Linguistic Generalization in Large Language Models? Experiments with Argument Structure

2023· preprint· en· W4388555939 on OpenAlexfundno aff
Michael Wilson, Jackson Petty, Robert Frank

Bibliographic record

VenuearXiv (Cornell University) · 2023
Typepreprint
Languageen
FieldComputer Science
TopicTopic Modeling
Canadian institutionsnot available
FundersNorthwestern UniversityUniversity of TorontoStony Brook UniversityNational Science FoundationYale UniversityHeinrich-Heine-Universität Düsseldorf
KeywordsArgument (complex analysis)VerbWord orderGeneralizationLinguisticsObject (grammar)Computer scienceSubject (documents)NounNatural language processingSpace (punctuation)Artificial intelligenceMathematicsPhilosophy

Abstract

fetched live from OpenAlex

Language models are typically evaluated on their success at predicting the distribution of specific words in specific contexts. Yet linguistic knowledge also encodes relationships between contexts, allowing inferences between word distributions. We investigate the degree to which pre-trained Transformer-based large language models (LLMs) represent such relationships, focusing on the domain of argument structure. We find that LLMs perform well in generalizing the distribution of a novel noun argument between related contexts that were seen during pre-training (e.g., the active object and passive subject of the verb spray), succeeding by making use of the semantically-organized structure of the embedding space for word embeddings. However, LLMs fail at generalizations between related contexts that have not been observed during pre-training, but which instantiate more abstract, but well-attested structural generalizations (e.g., between the active object and passive subject of an arbitrary verb). Instead, in this case, LLMs show a bias to generalize based on linear order. This finding points to a limitation with current models and points to a reason for which their training is data-intensive.s reported here are available at https://github.com/clay-lab/structural-alternations.

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)0.017
metaresearch head score (Gemma)0.068
Version: metacan-v3-hybrid-931329e0061cValidation 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: none
Teacher disagreement score0.017
Threshold uncertainty score0.088

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0170.068
Meta-epidemiology (narrow)0.0020.001
Meta-epidemiology (broad)0.0020.002
Bibliometrics0.0010.001
Science and technology studies0.0010.002
Scholarly communication0.0030.015
Open science0.0030.003
Research integrity0.0020.005
Insufficient payload (model declined to judge)0.0030.001

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 head0.076
GPT teacher head0.213
Teacher spread0.138 · 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 designSimulation or modeling
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

Citations2
Published2023
Admission routes1
Has abstractyes

Explore more

Same venuearXiv (Cornell University)Same topicTopic ModelingFrench-language works237,207