search

HowieHwong / TrustLLM

[ICML 2024] TrustLLM: Trustworthiness in Large Language Models
https://trustllmbenchmark.github.io/TrustLLM-Website/
MIT License
357 stars 30 forks source link

replacement of a GPT evaluator with an open-source evaluator #29

Open jinz2014 opened 3 weeks ago

jinz2014 commented 3 weeks ago

In the repository, the GPT models are used to automate the evaluation of some input data (e.g. utils/gpt_auto_eval.py). Could you please add an example of using open-source LLM evaluator ? Thanks.