So, you might be constructing a RAG system or utilizing an LLM to speak with paperwork. However customers usually ask: how can we belief the solutions?
Furthermore, we regularly hear about hallucinations, which undermine customers’ belief.
If we construct an utility however fail to indicate customers the place the solutions come from, the appliance would possibly turn out to be unusable in some instances.
On this article, I’ll share an method to deal with this concern. By linking each reply generated by the LLM to its supply textual content within the doc, we will construct transparency and belief. This methodology not solely offers clear proof for the solutions but additionally permits customers to confirm the outcomes straight inside the PDF.
Typically, the generated reply might not be completely correct, however with the ability to find the right supply textual content is already useful for the consumer.
Let’s take an instance of this paper from arxiv.org. We will think about this use case:
Step one on this method is to extract the textual content from the PDF in a structured format.
