News for hackers. Stuff that matters.
Re:Show HN: FastGraphRAG – Better RAG using good old PageRank by spdustin on Tuesday November 19, 2024 @03:10PM (#42187577)
My answer to this in my own pet project is to mask terms found by the NER pipeline from being corrected, replacing them with their entity type as a special token (e.g. [male person] or [commercial entity]). That alone dramatically improved grammar/spelling correction, especially because the grammatical "gist" of those masked words is preserved in the text presented to the LLM for "correction".

There are no comments on this comment yet.