CAREER: Underapproximate Refinement Types for Program Exploration and Understanding — NSF Award to Purdue University (IN, $391,123
Software development is rapidly changing, with developers increasingly delegating programming tasks to code generation tools powered by Large Language Models (LLMs). These systems often produce code that appears correct, but that actually contains subtle defects and inconsistencies with the developer’s intent, compromi
| Award title | CAREER: Underapproximate Refinement Types for Program Exploration and Understanding |
|---|---|
| Award ID | 2542188 |
| Awardee | Purdue University |
| City | WEST LAFAYETTE |
| State | IN |
| Amount obligated | $391,123 |
| Principal investigator | Benjamin Delaware |
| Program | Software & Hardware Foundation |
| Start date | 09/01/2026 |
| Abstract | Software development is rapidly changing, with developers increasingly delegating programming tasks to code generation tools powered by Large Language Models (LLMs). These systems often produce code that appears correct, but that actually contains subtle defects and inconsistencies with the developer’s intent, compromising the reliability and security of the generated program. As the role of software engineers moves away from writing code directly to inspecting generated programs, it is vital th |
| Source | NSF Awards |
$799/mo
Try NSFGrants →