首页|Patent Application Titled 'Generation Of Natural Language (Nl) Based Summaries U sing A Large Language Model (Llm) And Subsequent Modification Thereof For Attrib ution' Published Online (USPTO 20240320445)
Patent Application Titled 'Generation Of Natural Language (Nl) Based Summaries U sing A Large Language Model (Llm) And Subsequent Modification Thereof For Attrib ution' Published Online (USPTO 20240320445)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
Reporters obtained the following quote from the background information supplied by the inventors: “Large language models (LLMs) are particular types of machine learning models that can perform various natural language processing (NLP) tasks, such as language generation, machine translation, and questionanswering. Thes e LLMs are typically trained on enormous amounts of diverse data including data from, but not limited to, webpages, electronic books, software code, electronic news articles, and machine translation data. Accordingly, these LLMs leverage th e underlying data on which they were trained in performing these various NLP tas ks. For instance, in performing a language generation task, these LLMs can proce ss a natural language (NL) based query or prompt that is received from a client device, and generate a NL based response that is responsive to the NL based quer y or prompt and that is to be rendered at the client device. In generating the N L based response, these LLMs can inadvertently include content captured in the u nderlying data on which they were trained as a result of various factors. Howeve r, these LLMs are not designed to attribute this inadvertently included content to sources of the underlying data on which they were trained. Accordingly, there is a need in the art for new system(s) capable of attributing this inadvertentl y included content to the sources thereof.”
NETL
NSTL
