72 citations · 90 across the 7 of their papers we have counts for
Showing 2019Show all
2 papers · 1 filter
cs.CL2019
Universal Adversarial Triggers for Attacking and Analyzing NLP
Eric Wallace, Shi Feng, Nikhil Kandpal +2
Adversarial examples highlight model vulnerabilities and are useful for evaluation and interpretation. We define universal adversarial triggers: input-agnostic sequences of tokens…
cs.LG2019★ 6 cited
Misleading Failures of Partial-input Baselines
Shi Feng, Eric Wallace, Jordan Boyd-Graber
Recent work establishes dataset difficulty and removes annotation artifacts via partial-input baselines (e.g., hypothesis-only models for SNLI or question-only models for VQA). Whe…