LLM-eval-survey
The LLM-eval-survey is the official GitHub repository for the survey paper titled "A Survey on Evaluation of Large Language Models". This repository serves as a comprehensive resource for evaluating large language models (LLMs) across various tasks and domains.
Key Features:
- Comprehensive Evaluation: The repository organizes papers and resources related to the evaluation of LLMs, covering a wide range of tasks including natural language processing, reasoning, and more.
- Contribution Welcome: Users are encouraged to contribute by suggesting new benchmarks or improvements, with proper acknowledgment in the paper.
- Latest Updates: The repository is regularly updated with the latest research and findings in the field of LLM evaluation.
Benefits:
- Research Resource: A valuable resource for researchers and practitioners in the field of AI and natural language processing.
- Community Engagement: Encourages collaboration and community input to enhance the quality and comprehensiveness of the survey.
Highlights:
- Organized papers according to various evaluation criteria such as robustness, ethics, biases, and trustworthiness.
- Includes related projects and benchmarks for better summarization and evaluation of LLMs.
For more information, visit the GitHub repository.