THU-KEG/EvaluationPapers4ChatGPT
A curated collection of evaluation papers, datasets, and benchmarking tools for assessing ChatGPT and large language model performance.
Not currently ranked — collecting fresh signals.
star history
This repository aggregates research resources for evaluating ChatGPT and similar LLMs. It maintains ongoing datasets like ChatLog that track LLM responses over time, and introduces evaluation frameworks such as Language-Model-as-an-Examiner and the KoLA knowledge evaluation platform. The project also catalogs detection tools for identifying LLM-generated content and serves as a reference hub for the LLM evaluation community.
Frequently asked
- What is THU-KEG/EvaluationPapers4ChatGPT?
- A curated collection of evaluation papers, datasets, and benchmarking tools for assessing ChatGPT and large language model performance.
- Is EvaluationPapers4ChatGPT open source?
- Yes — THU-KEG/EvaluationPapers4ChatGPT is open source, released under the MIT license.
- How popular is EvaluationPapers4ChatGPT?
- THU-KEG/EvaluationPapers4ChatGPT has 455 stars on GitHub.
- Where can I find EvaluationPapers4ChatGPT?
- THU-KEG/EvaluationPapers4ChatGPT is on GitHub at https://github.com/THU-KEG/EvaluationPapers4ChatGPT.