Examples out of Thin Air: AI-Generated Dynamic Context to Assist Program Comprehension by Example
Name
3660829.3660845.pdf
Size
1.45 MB
Format
Adobe PDF
Checksum (MD5)
f87f5ce42c40214713d34b8dd7ce20a2
Author(s)
Mattis, Toni
Krebs, Eva
Rinard, Martin C.
Hirschfeld, Robert
Date Issued
March 11, 2024
Publisher
ACM|Companion Proceedings of the 8th International Conference on the Art, Science, and Engineering of Programming
Citation
Mattis, Toni, Krebs, Eva, Rinard, Martin C. and Hirschfeld, Robert. 2024. "Examples out of Thin Air: AI-Generated Dynamic Context to Assist Program Comprehension by Example."
Version
Final published version
Abstract
Programmers often benefit from the availability of concrete run-time data alongside abstract source code. However, programmers need to manually exercise the program to reach an interesting state or write code that reproducibly executes a functionality with concrete inputs to be able to observe concrete data.
This work aims to automate this process by leveraging generative AI. We present a framework and a preliminary Smalltalk-based prototype allowing programmers to obtain and run examples for the currently viewed source code section from a large language model.
Our approach demonstrates how locally hosted LLMs can be fine-tuned and used for such a task with reasonable computational effort while minimizing common problems like hallucinations and out-of-date knowledge. The framework has direct applications in example-based live programming, where it can suggest new examples, and in learning settings where novices need to know how to use certain functionality.
Description
Programming›Companion ’24, March 11–15, 2024, Lund, Sweden
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Terms of Use
Creative Commons Attribution
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1145/3660829.3660845
