Ambiguity Resolution with Human Feedback for Code Writing Tasks
International Conference on Computers in Education · 01.12.2025
DOI: 10.58459/icce.2025.5932 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Conference on Computers in Education, online erschienen am 01.12.2025. Verfasst von Aditey Nandan und 1 weiteren Autor:innen.
Abstract (Originalsprache)
Specifications for code writing tasks are usually expressed in natural language and may be ambiguous. Programmers must therefore develop the ability to recognize ambiguities in task specifications and resolve them by asking clarifying questions. We present and evaluate a prototype system, based on a novel technique (Ambiguity Resolution with Human Feedback: ARHF), that (1) suggests specific inputs on which a given task specification may be ambiguous, (2) seeks limited human feedback about the code' desired behavior on those inputs, and (3) attempts to generate code that resolves these ambiguities. We evaluate the efficacy of our prototype, and we discuss the implications of such assistive systems on Computer Science education.
Zitieren
APA
Nandan, A., & Kumar, V. (2025). Ambiguity Resolution with Human Feedback for Code Writing Tasks. International Conference on Computers in Education. https://doi.org/10.58459/icce.2025.5932
Vancouver
Nandan A, Kumar V. Ambiguity Resolution with Human Feedback for Code Writing Tasks. International Conference on Computers in Education. 2025. doi:10.58459/icce.2025.5932
BibTeX
@article{Nandan2025,
author = {Nandan, Aditey and Kumar, Viraj},
title = {Ambiguity Resolution with Human Feedback for Code Writing Tasks},
journal = {International Conference on Computers in Education},
year = {2025},
doi = {10.58459/icce.2025.5932}
}
EUVIMED