Patents by Inventor Reid Allen PRYZANT

Reid Allen PRYZANT 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).

  • Publication number: 20250111147
    Abstract: Systems and methods are provided for implementing automatic prompt optimization using textual gradients. In various embodiments, a feedback prompt, input into a large language model (“LLM”), is used to generate textual gradients that criticize a current prompt. The feedback prompt includes the current prompt and predictions that are incorrect compared with corresponding labels associated with minibatch data processed by the LLM using the current prompt. The textual gradients and current prompt are used in an editing prompt to the LLM to obtain a set of optimized prompts, which may be expanded using a paraphrasing prompt that is input into the LLM to generate a set of paraphrased prompts. A selection algorithm is used to select one or more optimized prompts from the set of optimized prompts and/or the set of paraphrased prompts, and the process is repeated with the selected one or more optimized prompts replacing the current prompt.
    Type: Application
    Filed: September 29, 2023
    Publication date: April 3, 2025
    Applicant: Microsoft Technology Licensing, LLC
    Inventors: Reid Allen PRYZANT, Jerry Zheng LI, Dan ITER, Yin Tat LEE, Chenguang ZHU, Nanshan ZENG, Anup Shirgaonkar
  • Publication number: 20240330165
    Abstract: Systems and methods are provided for implementing quality assurance for digital technologies using language model (“LM”)-based artificial intelligence (“AI”) and/or machine learning (“ML”) systems. In various embodiments, a first prompt is provided to an LM actor or attacker to cause the LM actor or attacker to generate interaction content for interacting with test software. Responses from the test software are then evaluated by an LM evaluator to produce evaluation results. In some examples, a second prompt is generated that includes the responses from the test software along with the evaluation criteria for the test software. When the second prompt is provided to the LM evaluator, the LM evaluator generates the evaluation results.
    Type: Application
    Filed: April 3, 2023
    Publication date: October 3, 2024
    Applicant: Microsoft Technology Licensing, LLC
    Inventors: Reid Allen PRYZANT, Yin Tat LEE, Chenguang ZHU, Sebastien BUBECK, Ronen ELDAN, Yuwei FANG, Dan ITER, Yichong XU, Yuanzhi LI, Yi ZHANG, Lijuan QIN, Nanshan ZENG, Xuedong HUANG
  • Publication number: 20230409826
    Abstract: Technologies related to computer-implemented conditional language models (CLMs) are described. A first CLM is trained to generate output texts based upon input texts and conditions. Output texts generated by the first CLM are included in a training set, and a second CLM is trained based upon the training set. The second CLM is then configured to receive input text and a condition and generate an output text based upon the input text and the condition.
    Type: Application
    Filed: June 16, 2022
    Publication date: December 21, 2023
    Inventors: Junyi CHAI, Konstantin GOLOBOKOV, Ye DONG, Reid Allen PRYZANT, Yi LIU
  • Publication number: 20230376789
    Abstract: Systems and techniques are provided for facilitating the automatic discovery and application of rules for refining the training of pretrained models, such as natural language processing models. Weak symbolic rules are automatically generated from the identification and processing of sparse labeled data by the pretrained model(s). Once the weak rules are generated, they are integrated into the model(s) via an attention mechanism to supplement the direct training performed by the sparse labeled data and to thereby boost a supervision signal generated by the sparse labeled data on any newly processed unlabeled data in the intended runtime environment(s) where the models are applied.
    Type: Application
    Filed: June 10, 2022
    Publication date: November 23, 2023
    Inventors: Reid Allen PRYZANT, Chenguang ZHU, Ziyi YANG, Yichong XU, Nanshan ZENG