@_philschmid They are good for what they are trained on, not so easy to integrate into a work flow. More room for improvement. So much interesting data is in scanned PDFs which are a challenge to read. Working on reading scanned hand drawn building designs
A Novel RAG Approach That Understands The Whole Document Context
RAG has rapidly evolved to be the standard way to apply LLMs in production. However, most methods are still limited because most existing methods retrieve only short contiguous chunks from a retrieval corpus, limiting holistic understanding of the overall document context.
A new approach named RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval (link in alt) proposes recursively embedding, clustering, and summarizing chunks of text, constructing a tree with differing levels of summarization from the bottom up.
At inference time, the RAPTOR model retrieves from this tree, integrating information across lengthy documents at different levels of abstraction.
Controlled experiments show that retrieval with recursive summaries offers significant improvements over traditional retrieval-augmented LMs on several tasks.
On question-answering tasks that involve complex, multi-step reasoning, we show state-of-the-art results; for example, by coupling RAPTOR retrieval with the use of GPT-4, we can improve the best performance on the QuALITY benchmark by 20% in absolute accuracy.
We will continue to see more methods like this one that are designed to improve document understanding and RAG. The good thing about this method is that it focuses on the retriever piece, while most of the other methods tinker with the context by adding noise or web results.
Walmart used an LLM (PaLM-2) generated embeddings for their DLRM to make product search better on https://t.co/dXWRG9d6Qa
They are about to push this out into their live website because the results were so good.
Noteworthy other firms have already done this such as Google
SaaS continues to be an attractive asset class for private equity and strategic buyers. #insurance#inSurTech#iot#5G#AI.
SEG 2023 Annual SaaS Report https://t.co/9S1pm4rp4P
Encouraging to see good satisfaction scores from those that use digital FNOl as reported in the JD Power 2022 US claims-digital experience-study. https://t.co/puuYWS8r0b #insurance#insurtech
Has to be easy use so Building MLGUI, user interfaces for machine learning applications is critical #insurance#insurtec#telco https://t.co/iHakaojTQ1 via @VentureBeat