QUALCOMM Incorporated (20240354346). SPECULATIVE DECODING IN AUTOREGRESSIVE GENERATIVE ARTIFICIAL INTELLIGENCE MODELS simplified abstract
Contents
SPECULATIVE DECODING IN AUTOREGRESSIVE GENERATIVE ARTIFICIAL INTELLIGENCE MODELS
Organization Name
Inventor(s)
Christopher Lott of San Diego CA (US)
Mingu Lee of San Diego CA (US)
Wonseok Jeon of San Diego CA (US)
Roland Memisevic of Toronto (CA)
SPECULATIVE DECODING IN AUTOREGRESSIVE GENERATIVE ARTIFICIAL INTELLIGENCE MODELS - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240354346 titled 'SPECULATIVE DECODING IN AUTOREGRESSIVE GENERATIVE ARTIFICIAL INTELLIGENCE MODELS
The abstract of this patent application describes techniques for generating a response to a query input in a generative artificial intelligence model.
- Receiving multiple sets of tokens generated based on an input prompt and a first generative artificial intelligence model.
- Selecting a set of tokens from the received sets using a second generative artificial intelligence model and recursive adjustment of a target distribution.
- Outputting the selected set of tokens as a response to the input prompt.
- Potential Applications:**
This technology can be applied in chatbots, virtual assistants, and automated customer service systems to generate responses to user queries.
- Problems Solved:**
This technology addresses the challenge of generating coherent and relevant responses in artificial intelligence models based on input prompts.
- Benefits:**
The benefits of this technology include improved efficiency in generating responses, enhanced user experience, and the ability to handle a large volume of queries effectively.
- Commercial Applications:**
Title: "Enhanced Response Generation Technology for Artificial Intelligence Models" This technology can be used in customer service applications, online chat platforms, and content generation tools to automate responses and improve communication efficiency.
- Questions about the Technology:**
1. How does this technology improve the response generation process in artificial intelligence models?
- This technology enhances response generation by selecting the most relevant set of tokens from multiple options based on input prompts.
2. What are the potential implications of using this technology in customer service applications?
- Implementing this technology in customer service applications can lead to faster response times, improved customer satisfaction, and reduced workload for human agents.
Original Abstract Submitted
certain aspects of the present disclosure provide techniques and apparatus for generating a response to a query input in a generative artificial intelligence model. an example method generally includes receiving a plurality of sets of tokens generated based on an input prompt and a first generative artificial intelligence model, each set of tokens in the plurality of sets of tokens corresponding to a candidate response to the input prompt; selecting, using a second generative artificial intelligence model and recursive adjustment of a target distribution associated with the received plurality of sets of tokens, a set of tokens from the plurality of sets of tokens; and outputting the selected set of tokens as a response to the input prompt.
