Large language models stay accurate when 90% of a coding prompt is deleted but frequently ignore a single quantifier flip that changes the problem, so their robustness blurs harmless noise and meaning-changing edits.
Adversarial ex- amples for evaluating reading comprehen- sion systems
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Small Edits, Big Consequences: Telling Good from Bad Robustness in Large Language Models
Large language models stay accurate when 90% of a coding prompt is deleted but frequently ignore a single quantifier flip that changes the problem, so their robustness blurs harmless noise and meaning-changing edits.