Holistic Evaluation of Language Models¶
Authors: Liang et al. Year: 2023 ArXiv/Link: https://arxiv.org/abs/2211.09110
Summary¶
Comprehensive evaluation framework (HELM) covering diverse dimensions of language model behavior and capabilities.
Key Concepts¶
- Evaluation framework
- Comprehensive assessment
- Multiple dimensions
- Benchmark diversity
- Model reliability
Impact¶
Established comprehensive evaluation methodology for LLMs
Category¶
Safety & Evaluation