Project Grant 2504354
Award Date
10/1/25
Completion Date
9/30/28
Dollars Obligated
$225K
Federal Agency
Division of Computing and Communication Foundations
Federal Grant Program
47.070
Assistance Type
Project Grant
Place of Performance
Fort Collins, CO 80521, USA
Similar Awards
This Project Grant award, provided by the National Science Foundation (NSF) through the Computer and Information Science and Engineering (CISE) program (CFDA 47.070), supports research to improve the code generation capabilities of large language models (LLMs). The primary goals are to develop novel techniques for evaluating the semantic properties of LLM-generated code, create a differentiable reward model to fine-tune LLMs for high-quality code generation, and leverage program analyses to...
This National Science Foundation (NSF) Computer and Information Science and Engineering (CISE) Federal Grant Program (CFDA 47.070) award to Purdue University will fund a $402,777 research project titled "CAREER: REGULARIZING LARGE LANGUAGE MODELS FOR SAFE AND RELIABLE PROGRAM GENERATION." The project aims to advance the understanding of limitations in using large language models (LLMs) for program generation and develop methods to enhance the correctness, safety, and robustness of...
This $875,000 Project Grant was awarded by the National Science Foundation (NSF) under the Computer and Information Science and Engineering (CISE) Federal Grant Program (CFDA 47.070) to the University of California, San Diego (UCSD). The project aims to develop new techniques for aligning large language models (LLMs) with formal specifications in order to generate high-quality computer code that provably matches user intent. Specifically, the project will: (1) develop grammar-aligned decoding...
This Project Grant award of $174,999 from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) will fund a unified, large language model (LLM)-empowered framework to systematically address software performance challenges. The key products and services to be delivered under this 2-year award (05/01/2025 - 04/30/2027) include: Advancing automation in performance testing, issue localization, and optimization for modern software...
This $100,000 Project Grant award from the National Science Foundation (NSF) Computer and Information Science and Engineering (CFDA 47.070) program aims to develop a holistic benchmarking infrastructure for evaluating large language models used in software engineering. The key activities include: Conducting surveys and interviews with the software engineering and machine learning research communities to gather requirements and understand barriers in evaluating large language models for code....
This $300,000 Project Grant award, funded by the National Science Foundation (NSF) under the Computer and Information Science and Engineering (CFDA 47.070) program, supports research to develop improved evaluation concepts and methods for assessing and enhancing the performance of large language models (LLMs). The key objectives are to: Identify a taxonomy of "evaluation concepts" to pinpoint areas where LLMs are underperforming, such as lack of detail or format issues. Develop...
This Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) aims to improve the evaluation and functionality of large language models (LLMs). The key products and services to be delivered include: Identifying a concept taxonomy to assess areas where LLMs are failing, such as lacking detail in responses. 2) Developing reward models to automatically evaluate and improve LLM responses according to the identified...
This $499,999 federal Project Grant award from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program (CFDA 47.070) will support collaborative research to investigate the theoretical foundations of compositional learning in large language models (LLMs) based on transformer architectures. The research aims to advance the understanding of how LLMs, such as GPT-4, LLAMA 2, and CLAUDE 3, can decompose complex tasks into simpler intermediate steps to...
This National Science Foundation (NSF) $900,000 "COLLABORATIVE RESEARCH: SHF: MEDIUM: NATURAL LANGUAGE MODELS WITH EXECUTION DATA FOR SOFTWARE TESTING" Project Grant, awarded under the Computer and Information Science and Engineering program (CFDA 47.070), aims to develop natural language processing (NLP) models to simplify the development and maintenance of software tests. Key objectives include test generation, completion, update, and migration across programming languages, targeting...
The National Science Foundation (NSF) awarded a $329,183 Project Grant to the College of William & Mary under the Computer and Information Science and Engineering (CFDA 47.070) program. The grant, awarded on October 1, 2023, will fund the development of a framework and methodology to enable researchers and software engineers to better interpret the behavior of AI-powered developer tools that leverage neural language models for source code. The project aims to generate global and local...