WikiContradict Benchmark

What is WikiContradict?

WikiContradict is a benchmark consisting of 253 high-quality, human-annotated instances designed to assess LLM performance when augmented with retrieved…

Released

2024-06-19

Evaluates

推理, Reasoning, NeurIPS 2024, 大语言模型, LLM, 事实可靠性, Factual Reliability, 逻辑推理, 不支持, Unsupported

Openness

unknown

Importer

OpenCompass Hub

Reported scores

0

Source provenance

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

WikiContradict paper and dataset

• Paper https://arxiv.org/abs/2406.13805
• Dataset https://huggingface.co/datasets/ibm/Wikipedia_contradict_benchmark

Which sources cite WikiContradict?

• WikiContradict

Related 推理, Reasoning, NeurIPS 2024, 大语言模型, LLM, 事实可靠性, Factual Reliability, 逻辑推理, 不支持, Unsupported benchmarks

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