ALEXANDRIA, Va., May 26 -- United States Patent no. 12,639,520, issued on May 26, was assigned to Intuit Inc. (Mountain View, Calif.).
"Large language model explainability via counterfactuals" was invented by Yair Horesh (Kfar-Saba, Israel), Aleksandr Kim (Tel Aviv, Israel), Meghan Rose Khemaissa Mergui Lahmi (Tel Aviv, Israel) and Jonathan Rabin (Tel Aviv, Israel).
According to the abstract* released by the U.S. Patent & Trademark Office: "A method includes obtaining a prompt to a field large language model (LLM) and a corresponding original response generated by the field LLM. A first phrase is selected from the prompt. A syntactic phrase set, and a semantic phrase set are obtained for the first phrase from a domain corpus. A counterfac...