New ask Hacker News story: Ask HN: What is the state of AI data annotation of pdf documents using LLM
Ask HN: What is the state of AI data annotation of pdf documents using LLM
2 by ak_111 | 0 comments on Hacker News.
As an example I have a corpus of scientific papers for which I would like to label the segments that contain an application to organic chemistry. Assuming the labeling is not very sophisticated (literally "this passage contains an application to organic chemistry") Do I need to train models to detect and label these segments or is it viable to feed into an LLM model with no prior training? What are currently the best/cheapest services/libraries that help with this kind of workflow that doesn't involve reinventing the wheel?
2 by ak_111 | 0 comments on Hacker News.
As an example I have a corpus of scientific papers for which I would like to label the segments that contain an application to organic chemistry. Assuming the labeling is not very sophisticated (literally "this passage contains an application to organic chemistry") Do I need to train models to detect and label these segments or is it viable to feed into an LLM model with no prior training? What are currently the best/cheapest services/libraries that help with this kind of workflow that doesn't involve reinventing the wheel?
Comments
Post a Comment