AMBROSIA Benchmark

What is AMBROSIA?

AMBROSIA is a new benchmark for recognizing and interpreting ambiguous requests in text-to-SQL. It contains questions showcasing three different types of…

Released

2024-06-27

Evaluates

推理, Reasoning, NeurIPS 2024, 大语言模型, LLM, 代码工程, Code, 不支持, Unsupported

Openness

unknown

Importer

OpenCompass Hub

Reported scores

0

Source provenance

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

AMBROSIA paper and code

• Paper https://arxiv.org/abs/2406.19073
• Code https://github.com/saparina/ambrosia

Which sources cite AMBROSIA?

• AMBROSIA

Related 推理, Reasoning, NeurIPS 2024, 大语言模型, LLM, 代码工程, Code, 不支持, Unsupported benchmarks

• A-Bench
• A-OKVQA
• AbsPyramid
• ActionAtlas
• ActiveFly-Bench
• Ada-LEval
• AdvancedMathBench
• AECBench