Chalkidis on ChatGPT Cannot (Yet) Pass LexGLUE Benchmark

Ilias Chalkidis (University of Copenhagen) has posted “ChatGPT May Pass the Bar Exam Soon, but Has a Long Way to Go for the LexGLUE Benchmark” on SSRN. Here is the abstract:

Following the hype around OpenAI’s ChatGPT conversational agent, the last straw in the recent development of Large Language Models (LLMs) that demonstrate emergent unprecedented zero-shot capabilities, we audit the latest OpenAI’s GPT-3.5 model, ‘gpt-3.5-turbo’, the first available ChatGPT model, in the LexGLUE benchmark in a zero-shot fashion providing examples in a templated instruction-following format. The results indicate that ChatGPT achieves an average micro-F1 score of 49.0% across LexGLUE tasks, surpassing the baseline guessing rates. Notably, the model performs exceptionally well in some datasets, achieving micro-F1 scores of 62.8% and 70.1% in the ECtHR B and LEDGAR datasets, respectively. The code base and model predictions are available at