-
-
Notifications
You must be signed in to change notification settings - Fork 94
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
There is a significant difference between feed shot and zero shot #371
Comments
Please copy-paste your code and config (formatted with ``` ```) into this thread. |
examples.yml:
[nlp] [components] [components.llm_ner] [components.llm_ner.task] [components.llm_ner.task.examples] [components.llm_ner.model] zeroshot.cfg: [nlp] [components] [components.llm_ner] [components.llm_ner.task] [components.llm_ner.model] run_pipeline.py import os import typer from spacy_llm.util import assemble Arg = typer.Argument def run_pipeline(
if name == "main": !python run_pipeline.py |
The complete code is included in the attachment |
Hello, I have discovered a problem. Just treat me as a zero shot. Once fewshot reports an error. Why did providing fewshot knowledge report an error. |
It's difficult to diagnose why fewshotting yields worse results here. I recommend debugging with one example at a time and looking into the raw output received from the model (see here on how to do that). The fact that you get no entities at all if you include fewshot examples indicate that the LLM might have issues understanding those examples, or that the output produced by the LLM if those examples are included is incoherent and cannot be parsed. Either way the best way forward is to have a closer look at how both the prompt and the response look like if you add one example at a time. |
Thank you very much for your answers. It would be even better if we could add a Chinese model later on |
If I use fewshot. It was found that the extracted content was much worse than the results extracted by zero shot。


code.zip
The attachment is my code。
The text was updated successfully, but these errors were encountered: