Working on CiteLLM, an API that extracts structured data from PDFs and returns citations for each field (page + coordinates + source snippet + confidence).
Instead of blindly trusting the LLM, you can verify every value by linking it back to its exact location in the original PDF.
Every extracted field comes with a precise citation back to the source document (page + snippet + bounding box + confidence score) so reviewers can verify where each value came from.
Hallucinations get flagged automatically because there's no supporting text in the source.
The goal is to make HITL fast and not have reviewers read through the whole document.
Working on CiteLLM, an API that extracts structured data from PDFs and returns citations for each field (page + coordinates + source snippet + confidence).
Instead of blindly trusting the LLM, you can verify every value by linking it back to its exact location in the original PDF.
I've been working on this problem with https://citellm.com, specifically for PDFs.
Instead of relying on the LLM answer alone, each extracted field links to its source in the original document (page number + highlighted snippet + confidence score).
Checking any claim becomes simple: click and see the exact source.
I'm working on SuperCurate (https://getsupercurate.com), which is geared towards note retrieval and curation rather than note creation.
Think filing cabinet for your notes, web clippings, images and PDFs.
I wanted fast search and filters for my Evernote archive so I could drill down and surface exactly what I was looking for.
Working on CiteLLM, an API that extracts structured data from PDFs and returns citations for each field (page + coordinates + source snippet + confidence).
Instead of blindly trusting the LLM, you can verify every value by linking it back to its exact location in the original PDF.
reply