search

mayubo2333 / LLM-IE

EMNLP'2023 (Findings): Large Language Model Is Not a Good Few-shot Information Extractor, but a Good Reranker for Hard Samples!
33 stars 2 forks source link

there is no SLM related code? #4

Closed hhy150 closed 4 months ago

hhy150 commented 4 months ago

Hello, thank you very much for being able to open source code!!! But it seems that there is no SLM related code provided here, I wonder if it can be provided?

mayubo2333 commented 4 months ago

Hello, thank you very much for being able to open source code!!! But it seems that there is no SLM related code provided here, I wonder if it can be provided?

Thanks for your interest on our work. I can consider to release SLM related code later but there is no clear timeline for it in the near future (I'm a little busy recently).

From my understanding, it will not take your much time to write your own SLM related code because SLM methods used are classical ones (like vanilla fine-tuning, FSLS and KnowPrompt). I highly recommend you to implement these method by your own and then save the predictions as the format examples shown in ./SLM_results before using LLM reranking.

hhy150 commented 4 months ago

Thank you for your reply. You make sense. I can run an SLM model myself, so there is no need to provide any more code. Thank you!