MétaCan
Menu
Back to cohort

On the Transformation of Latent Space in Fine-Tuned NLP Models

2022· article· en· W4385573233 on OpenAlexaff
Nadir Durrani, Hassan Sajjad, Fahim Dalvi, Firoj Alam

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicTopic Modeling
Canadian institutionsDalhousie University
Fundersnot available
KeywordsComputer scienceArtificial intelligenceSpace (punctuation)Similarity (geometry)Task (project management)Cluster analysisTransformation (genetics)Function (biology)Probabilistic latent semantic analysisNatural language processingClass (philosophy)Machine learning

Abstract

fetched live from OpenAlex

We study the evolution of latent space in finetuned NLP models.Different from the commonly used probing-framework, we opt for an unsupervised method to analyze representations.More specifically, we discover latent concepts in the representational space using hierarchical clustering.We then use an alignment function to gauge the similarity between the latent space of a pre-trained model and its finetuned version.We use traditional linguistic concepts to facilitate our understanding and also study how the model space transforms towards task-specific information.We perform a thorough analysis, comparing pre-trained and finetuned models across three models and three downstream tasks.The notable findings of our work are: i) the latent space of the higher layers evolve towards task-specific concepts, ii) whereas the lower layers retain generic concepts acquired in the pre-trained model, iii) we discovered that some concepts in the higher layers acquire polarity towards the output class, and iv) that these concepts can be used for generating adversarial triggers.

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)0.002
metaresearch head score (Gemma)0.016
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.005
Threshold uncertainty score0.012

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0020.016
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.000
Science and technology studies0.0010.002
Scholarly communication0.0020.004
Open science0.0010.002
Research integrity0.0010.003
Insufficient payload (model declined to judge)0.0020.000

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 head0.041
GPT teacher head0.227
Teacher spread0.186 · 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 designObservational
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
Published2022
Admission routes1
Has abstractyes

Explore more

Same topicTopic ModelingFrench-language works237,207