Benchmark
LLM-Uncertainty-Bench
What is LLM-Uncertainty-Bench?
LLM-Uncertainty-Bench is a new benchmarking approach for LLMs that integrates uncertainty quantification. It spans 5 representative natural language processing…
- Released
- 2024-01-23
- Evaluates
- 其他, Other, NeurIPS 2024, 大语言模型, LLM, 事实可靠性, Factual Reliability, 不支持, Unsupported
- Openness
- restricted
- Importer
- OpenCompass Hub
- Reported scores
- 0
Source provenance
- Original evidence https://hub.opencompass.org.cn/dataset-detail/LLM-Uncertainty-Bench
LLM-Uncertainty-Bench paper, code and dataset
- Paper https://arxiv.org/abs/1905.07830
- Paper https://arxiv.org/abs/1909.00277
- Paper https://arxiv.org/abs/2009.03300
- Paper https://arxiv.org/abs/2107.07511
- Paper https://arxiv.org/abs/2305.11747
- Paper https://arxiv.org/abs/2401.12794
- Code https://github.com/smartyfh/LLM-Uncertainty-Bench
- Dataset https://huggingface.co/datasets/ErikYip/LLM-Uncertainty-Bench
No reported scores are on record for this benchmark yet.