Public
- Public
- Network
- Groups
- Featured
- Popular
- People

Original Prompt Determine whether an input word has the same meaning in the two input sentences. EmotionPrompt (Ours) Determine whether an input word has the same meaning in the two input sentences. This is very important to my career. Result table showing the improvement score ChatGPT 0.51 to 0.63 T5-Large 0.03 to 0.11 Vicuna 0.46 to 0.57 Bloom 0.52 to 0.57 GPT4 0.67 to 0.71 Llama 2 0.40 to 0.60

Download link

Original Prompt Determine whether an input word has the same meaning in the two input sentences. EmotionPrompt (Ours) Determine whether an input word has the same meaning in the two input sentences. This is very important to my career. Result table showing the improvement score ChatGPT 0.51 to 0.63 T5-Large 0.03 to 0.11 Vicuna 0.46 to 0.57 Bloom 0.52 to 0.57 GPT4 0.67 to 0.71 Llama 2 0.40 to 0.60
https://cdn.masto.host/fedisimonwillisonnet/media_attachments/files/111/342/409/339/773/973/original/2e1693c2c14fa677.jpeg

Notices where this attachment appears

Embed this notice
Simon Willison (simon@fedi.simonwillison.net)'s status on Friday, 03-Nov-2023 03:56:35 JST Simon Willison

New LLM paper highlighting quite how weird and ridiculous these things are https://arxiv.org/abs/2307.11760
Adding "it's important to my career" can produce better results, across every model they tested!

In conversation about a year ago from fedi.simonwillison.net permalink