MétaCan
Menu
Back to cohort

Impact of Adversarial Training on Robustness and Generalizability of Language Models

2023· article· en· W4385572282 on OpenAlexaff
Enes Altınışık, Hassan Sajjad, Hüsrev Taha Sencar, Safa Messaoud, Sanjay Chawla

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicAdversarial Robustness in Machine Learning
Canadian institutionsDalhousie University
Fundersnot available
KeywordsAdversarial systemGeneralizability theoryComputer scienceEmbeddingRobustness (evolution)Artificial intelligenceGeneralizationTransformerMachine learningTraining setMathematicsEngineering

Abstract

fetched live from OpenAlex

Adversarial training is widely acknowledged as the most effective defense against adversarial attacks.However, it is also well established that achieving both robustness and generalization in adversarially trained models involves a trade-off.The goal of this work is to provide an in depth comparison of different approaches for adversarial training in language models.Specifically, we study the effect of pretraining data augmentation as well as training time input perturbations vs. embedding space perturbations on the robustness and generalization of transformer-based language models.Our findings suggest that better robustness can be achieved by pre-training data augmentation or by training with input space perturbation.However, training with embedding space perturbation significantly improves generalization.A linguistic correlation analysis of neurons of the learned models reveal that the improved generalization is due to 'more specialized' neurons.To the best of our knowledge, this is the first work to carry out a deep qualitative analysis of different methods of generating adversarial examples in adversarial training of language models.

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)0.007
metaresearch head score (Gemma)0.051
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 score0.007
Threshold uncertainty score0.039

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0070.051
Meta-epidemiology (narrow)0.0020.001
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.000
Science and technology studies0.0010.003
Scholarly communication0.0010.003
Open science0.0010.004
Research integrity0.0020.004
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 head0.042
GPT teacher head0.319
Teacher spread0.277 · 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

Citations7
Published2023
Admission routes1
Has abstractyes

Explore more

Same topicAdversarial Robustness in Machine LearningFrench-language works237,207