pith. sign in

Title resolution pending

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CL 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Universal Adversarial Triggers

cs.CL · 2026-05-18 · unverdicted · novelty 5.0

Combines POS filtering and perplexity loss to generate sensible universal adversarial triggers that drop SST sentiment accuracy to 0.04-0.12, with adversarial training raising it to 0.48.

citing papers explorer

Showing 1 of 1 citing paper.

  • Universal Adversarial Triggers cs.CL · 2026-05-18 · unverdicted · none · ref 8

    Combines POS filtering and perplexity loss to generate sensible universal adversarial triggers that drop SST sentiment accuracy to 0.04-0.12, with adversarial training raising it to 0.48.