Benchmark

DOVE Benchmark

What is DOVE?

DOVE (Dataset Of Variation Evaluation) is a large-scale dataset containing prompt perturbations of various evaluation benchmarks.

Released: 2025-03-04
Evaluates: 其他, Other, LLM敏感性评估, 大语言模型, LLM, 指令遵循, Instruction Following, 不支持, Unsupported
Openness: unknown
Importer: OpenCompass Hub
Reported scores: 0

Source provenance

Original evidence https://hub.opencompass.org.cn/dataset-detail/DOVE

DOVE paper, code and dataset

Paper https://arxiv.org/abs/2503.01622
Code https://github.com/SLAB-NLP/DOVE
Dataset https://huggingface.co/datasets/nlphuji/DOVE
Dataset https://huggingface.co/datasets/nlphuji/DOVE_Lite

No reported scores are on record for this benchmark yet.

Which sources cite DOVE?

DOVE

Related 其他, Other, LLM敏感性评估, 大语言模型, LLM, 指令遵循, Instruction Following, 不支持, Unsupported benchmarks