add human evaluation results

README.md

@@ -49,6 +49,16 @@ This JSON file has the same format as Alpaca data, except the output is generate
 
 [`unnatural_instruction_gpt4_data.json`](./data/unnatural_instruction_gpt4_data.json) contains 9K instruction-following data generated by GPT-4 with prompts in Unnatural Instruction. This JSON file has the same format as Alpaca data.
 
+## How Good is the Data?
+
+Human evaluation was performed on model generation results using Amazon Mechanical Turk following Helpfulness, Honestness and Harmlessness criteria by [Anthropic AI](https://arxiv.org/abs/2112.00861). The results are summarized as follows:
+- Two instruction-tuned LLaMA models were compared, fine-tuned on data generated by GPT-4 and GPT-3 respectively.
+- LLaMA-GPT-4 performs substantially better than LLaMA-GPT-3 in the "Helpfulness" criterion.
+- LLaMA-GPT-4 performs similarly to the original GPT-4 in all three criteria, suggesting a promising direction for developing state-of-the-art instruction-following LLMs.
+
+![LLaMA-GPT4 vs Alpaca (i.e., LLaMA-GPT3)](static/pie_llama_gpt3_vs_llam_gpt4.png )
+![LLaMA-GPT4 vs GPT-4](static/pie_llama_gpt4_vs_gpt4.png )
+
 ## Fine-tuning with the data
 We follow the same reciple to fine-tune LLaMA as Alpaca using standard Hugging Face training code.