• Home
  • Technology
  • Gaming
  • Entertainment
  • World & Business
  • Science
  • Sports
  • AI
HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI
    AI
    Reaction

    Model described as deriving values not stated in documents

    A user says it can calculate a product's yearly cost from its monthly cost, citing examples in a video.

    Rohan PaulRP
    SantiagoSA
    2 Sources, ,

    TLDR

    A user describes a model that “extracts” values not stated in a document by calculating them from values that are. For example, they say it can derive a product's yearly cost from its monthly cost. The user says a video shows other examples and that the model appears able to infer more complex formulas.

    Combined views

    7.7K

    2 Sources, first seen 2h ago

    Combined views

    7.7K

    2 Sources, first seen 2h ago

    44 likes
    2h ago
    first seen 2h ago
    44 likes
    9 comments
    42 saves
    1 reposts
    Featured Source
    9 comments
    42 saves
    1 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet

    2 Sources

    Santiago@svpinoThis is very clever: It's a model that "extracts" values that don't exist in a document but can be derived from the values that do exist. For example, you can ask for the yearly cost of using a product, and it will automatically compute it from the monthly cost. The video shows a bunch of cool examples. It looks like it can infer really convoluted and sophisticated formulas.2h
    Rohan Paul@rohanpaul_aiMost document AI is built to answer one question: where is this number on the page? But the number people need often isn't on the page. It has to be calculated from the numbers that are. Higher-Order Extraction from Unsiloed does that calculation. It calculates numbers a document never prints by generating deterministic code from page values. e.g. you ask for the final figure, it reads the raw values from the document, writes code that combines them, and runs that code to get the answer. Every result traces back to the page. There's a second check. If the document happens to print the answer somewhere, the system compares it with its own result. If they match, confidence goes up. If they don't, confidence drops to zero.40m

    2 Sources

    Santiago@svpinoThis is very clever: It's a model that "extracts" values that don't exist in a document but can be derived from the values that do exist. For example, you can ask for the yearly cost of using a product, and it will automatically compute it from the monthly cost. The video shows a bunch of cool examples. It looks like it can infer really convoluted and sophisticated formulas.2h
    Rohan Paul@rohanpaul_aiMost document AI is built to answer one question: where is this number on the page? But the number people need often isn't on the page. It has to be calculated from the numbers that are. Higher-Order Extraction from Unsiloed does that calculation. It calculates numbers a document never prints by generating deterministic code from page values. e.g. you ask for the final figure, it reads the raw values from the document, writes code that combines them, and runs that code to get the answer. Every result traces back to the page. There's a second check. If the document happens to print the answer somewhere, the system compares it with its own result. If they match, confidence goes up. If they don't, confidence drops to zero.40m