Towards Open Natural Language Feedback Generation for Novice Programmers using Large Language Models
Charles Koutcheme · 2022
Automated feedback on programming exercises has traditionally focused on correctness of submitted exercises. The correctness has been inferred, for example, based on a set of unit tests. Recent advances in the area of providing feedback have suggested relying on large language models for building feedback. In this poster, we present an approach for automatically constructed formative feedback, written in natural language, that builds on two streams of research: (1) automatic program repair, and (2) automatically generating descriptions of programs. Building on combining these two streams, we propose a new approach for constructing written formative feedback on programming exercise submissions.