MétaCan
Menu
Back to cohort
Record W3196986263 · doi:10.1162/tacl_a_00519

Neuron-level Interpretation of Deep NLP Models: A Survey

2022· article· en· W3196986263 on OpenAlexaff
Hassan Sajjad, Nadir Durrani, Fahim Dalvi

Bibliographic record

VenueTransactions of the Association for Computational Linguistics · 2022
Typearticle
Languageen
FieldComputer Science
TopicExplainable Artificial Intelligence (XAI)
Canadian institutionsDalhousie University
Fundersnot available
KeywordsInterpretabilityComputer scienceRepresentation (politics)Artificial intelligenceDomain (mathematical analysis)Adaptation (eye)Interpretation (philosophy)Artificial neural networkDomain adaptationMachine learningNatural language processingData scienceNeuroscience

Abstract

fetched live from OpenAlex

Abstract The proliferation of Deep Neural Networks in various domains has seen an increased need for interpretability of these models. Preliminary work done along this line, and papers that surveyed such, are focused on high-level representation analysis. However, a recent branch of work has concentrated on interpretability at a more granular level of analyzing neurons within these models. In this paper, we survey the work done on neuron analysis including: i) methods to discover and understand neurons in a network; ii) evaluation methods; iii) major findings including cross architectural comparisons that neuron analysis has unraveled; iv) applications of neuron probing such as: controlling the model, domain adaptation, and so forth; and v) a discussion on open issues and future research directions.

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)0.006
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Not applicable · Consensus signal: none
GenreCandidate signal: Review · Consensus signal: none
Teacher disagreement score0.004
Threshold uncertainty score0.013

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0020.006
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0020.002
Science and technology studies0.0000.002
Scholarly communication0.0040.005
Open science0.0030.002
Research integrity0.0010.002
Insufficient payload (model declined to judge)0.0040.001

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 head0.055
GPT teacher head0.284
Teacher spread0.230 · 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 designNot applicable
Domainnot available
GenreReview

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

Citations38
Published2022
Admission routes1
Has abstractyes

Explore more

Same venueTransactions of the Association for Computational LinguisticsSame topicExplainable Artificial Intelligence (XAI)French-language works237,207