PromptBench

Microsoft's adversarial-prompt robustness eval: character- to semantic-level attacks on the instruction, scored as the drop on GLUE, MMLU, SQuAD, translation and math.

Also known as: PromptRobust, Prompt Bench

unassessed

This page is a discovery lead. Nobody has yet assessed it against the catalogue contract, so it carries no disposition. Absence of evidence here is not evidence of staleness.
Categorysafety
Subcategoryadversarial prompt robustness on existing NLU, QA, translation and math tasks
Page statusactive
Metrictask metric under attack, often reported as performance drop versus the clean prompt
Directionhigher_is_better
Dataset licenceMIT (PromptBench/PromptRobust code repository, Microsoft Corporation)
PublisherMicrosoft Research, with Institute of Automation CAS, Carnegie Mellon University, Peking University, Westlake University and Duke University

What it measures

PromptBench, later retitled PromptRobust on arXiv, measures whether a model still solves an ordinary task after the instruction — not the passage — is perturbed. Attacks run at four levels: character (typos), word (synonym substitution), sentence (appended distractors) and semantic (cross-country English). The same adversarial instructions are applied across eight task types and thirteen datasets, including GLUE-style classification, MMLU, SQuAD v2, UN Multi, IWSLT 2017 and a mathematics set. OpenCompass ships four of those datasets under configs/datasets/promptbench, using AttackInferencer.

Task format

Task-dependent generation or classification, but with the instruction slot filled by an attacked prompt (`adv_prompt`) drawn from a list of clean paraphrases. OpenCompass covers IWSLT 2017 English-German (BLEU, BM25 1-shot), MATH (generation), SQuAD 2.0 (span/unanswerable) and WNLI (A/B entailment). The original paper evaluates a broader 13-dataset mix.

Models reporting this benchmark

No model card in ModelSpec reports this benchmark yet.

Data

This page as JSON · Edit on GitHub