18144802. MATHEMATICAL REASONING USING LARGE LANGUAGE MODELS simplified abstract (Microsoft Technology Licensing, LLC)
MATHEMATICAL REASONING USING LARGE LANGUAGE MODELS
Organization Name
Microsoft Technology Licensing, LLC
Inventor(s)
Shima Imani of Sammamish WA (US)
Harsh Shrivastava of Redmond WA (US)
MATHEMATICAL REASONING USING LARGE LANGUAGE MODELS - A simplified explanation of the abstract
This abstract first appeared for US patent application 18144802 titled 'MATHEMATICAL REASONING USING LARGE LANGUAGE MODELS
Simplified Explanation
The patent application describes techniques for an AI system called Large Language Model (LLM) to solve mathematical problems accurately and reliably. It involves transforming an initial query into a template query, sending multiple prompts to the LLM, receiving multiple results with analytical expressions, evaluating these expressions, and achieving a consensus before outputting the solution.
- The AI system uses a Large Language Model (LLM) to solve mathematical problems.
- Initial query is transformed into a template query with variables.
- Multiple prompts are sent to the LLM, each contextually related to the template query.
- Multiple results with analytical expressions are received from the LLM.
- Expressions are evaluated using a numerical evaluation tool with randomly sampled values.
- Consensus is achieved when evaluated expressions satisfy a consensus condition.
- Original inputs are evaluated with the expressions to output the solution.
Potential Applications
This technology can be applied in various fields such as education, research, engineering, and finance where accurate and reliable solutions to mathematical problems are required.
Problems Solved
This technology addresses the challenges of accurately and reliably solving complex mathematical problems using AI systems like LLM.
Benefits
The benefits of this technology include improved accuracy, reliability, and efficiency in solving mathematical problems, saving time and effort for users.
Commercial Applications
Title: Enhanced Mathematical Problem Solving with AI This technology can be commercialized in educational software, financial analysis tools, engineering applications, and research platforms to provide advanced mathematical problem-solving capabilities.
Questions about the Technology
How does the AI system achieve consensus in solving mathematical problems?
The AI system achieves consensus by evaluating multiple expressions and ensuring they consistently match over a set number of experiments or trials.
What are the potential implications of using this technology in educational settings?
Using this technology in education can enhance students' learning experience by providing accurate and reliable solutions to complex mathematical problems.
Original Abstract Submitted
Disclosed are techniques for an AI system with a large language mode (LLM) with improved accuracy and reliability in solving mathematical problems. An initial query is transformed into a template query by replacing the original input values with variables. Multiple prompts are sent to the LLM, each being different from one another, and contextually related to the template query. Multiple results are responsively received from the LLM, each result including an analytical expression to solve the mathematical problem. Each of the expressions is evaluated using a numerical evaluation tool with variables of the expression being assigned a common set of randomly sampled values. A consensus is achieved when the evaluated expressions satisfy a consensus condition, such as when all outputs match consistently over N experiments or trials. After the consensus condition is reached, the original inputs are evaluated with one or more of the expressions, and the solution is output.