Patents by Inventor Clemence Lanfranchi

Clemence Lanfranchi has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Patent number: 12775613
    Abstract: Here is an innovative way to generate a finetuning corpus that maximizes the accuracy of a target large language model (LLM) that generates a database statement. From a natural language request, the target LLM infers an incorrect database statement that, based on a first database schema, could not satisfy a technical requirement. Based on the natural language request, a correct database statement is generated that, based on a second database schema, could satisfy the technical requirement. For the second database schema, a restatement of the natural language request is generated. In inputs during finetuning, the target LLM accepts: the correct database statement, the incorrect database statement, and the restatement of the natural language request.
    Type: Grant
    Filed: August 30, 2024
    Date of Patent: October 27, 2026
    Assignee: Oracle International Corporation
    Inventors: Clemence Lanfranchi, Damien Hilloulin, Rhicheek Patra, Sungpack Hong, Hassan Chafi, Yakupitiyage Don Dharmasir, Cong Duy Vu Hoang, Gioacchino Tangari, Thanh Vu, Thanh Long Duong
  • Patent number: 12754888
    Abstract: In an embodiment, a computer generates a lexical prompt for a large language model (LLM) that accepts the prompt as input, which causes the LLM to generatively infer a hybrid table schema that contains natural language that describes a data table. The prompt may contain linguistic exemplar(s) that are generated from statically or dynamically selected predefined data tables. As discussed herein, task accuracy of computer inferencing is increased by novel static exemplar(s), and semantic accuracy of computer inferencing is increased by novel dynamic selection of most semantically similar dynamic exemplar(s). Dynamic selection of exemplars is accelerated by indexing of learned semantic vector encodings of predefined and new data tables.
    Type: Grant
    Filed: March 5, 2024
    Date of Patent: October 6, 2026
    Assignee: Oracle International Corporation
    Inventors: Clemence Lanfranchi, Marcel Gwerder, Margherita Musumeci
  • Publication number: 20260064671
    Abstract: Here is an innovative way to generate a finetuning corpus that maximizes the accuracy of a target large language model (LLM) that generates a database statement. From a natural language request, the target LLM infers an incorrect database statement that, based on a first database schema, could not satisfy a technical requirement. Based on the natural language request, a correct database statement is generated that, based on a second database schema, could satisfy the technical requirement. For the second database schema, a restatement of the natural language request is generated. In inputs during finetuning, the target LLM accepts: the correct database statement, the incorrect database statement, and the restatement of the natural language request.
    Type: Application
    Filed: August 30, 2024
    Publication date: March 5, 2026
    Inventors: Clemence Lanfranchi, Damien Hilloulin, Rhicheek Patra, Sungpack Hong, Hassan Chafi, Yakupitiyage Don Dharmasir, Cong Duy Vu Hoang, Gioacchino Tangari, Thanh Vu, Thanh Long Duong
  • Publication number: 20250284670
    Abstract: In an embodiment, a computer generates a lexical prompt for a large language model (LLM) that accepts the prompt as input, which causes the LLM to generatively infer a hybrid table schema that contains natural language that describes a data table. The prompt may contain linguistic exemplar(s) that are generated from statically or dynamically selected predefined data tables. As discussed herein, task accuracy of computer inferencing is increased by novel static exemplar(s), and semantic accuracy of computer inferencing is increased by novel dynamic selection of most semantically similar dynamic exemplar(s). Dynamic selection of exemplars is accelerated by indexing of learned semantic vector encodings of predefined and new data tables.
    Type: Application
    Filed: March 5, 2024
    Publication date: September 11, 2025
    Inventors: Clemence Lanfranchi, Marcel Gwerder, Margherita Musumeci
  • Publication number: 20250245487
    Abstract: Techniques for automatically generating tests using a large language model (LLM) are provided. In one technique, a set of positive training samples for training a first LLM is stored. Based on that set, a set of correction training samples is generated, each sample including an error from processing a faulty test of particular code. A second LLM is trained based on those samples. A first test, of code, that was generated by the first LLM is received. A first result of processing the first test is generated. In response to determining that the first result indicates an error in processing the first test, a first correction prompt is generated based on the first result. The first correction prompt is input into the second LLM that outputs a second test that is a corrected version of the first test. A second result of processing the second test is generated.
    Type: Application
    Filed: January 31, 2024
    Publication date: July 31, 2025
    Inventors: Damien Hilloulin, Jonas Schweizer, Clemence Lanfranchi