notesum.ai

Published at November 22

Leveraging LLMs for Legacy Code Modernization: Challenges and Opportunities for LLM-Generated Documentation

cs.SE

Released Date: November 22, 2024

Authors: Colin Diggs¹, Michael Doyle¹, Amit Madan¹, Siggy Scott¹, Emily Escamilla¹, Jacob Zimmer¹, Naveed Nekoo¹, Paul Ursino¹, Michael Bartholf¹, Zachary Robin¹, Anand Patel¹, Chris Glasz¹, William Macke¹, Paul Kirk¹, Jasper Phillips¹, Arun Sridharan¹, Doug Wendt¹, Scott Rosen¹, Nitin Naik¹, Justin F. Brunelle¹, Samruddhi Thaker¹

Aff.: ¹The MITRE Corporation

Arxiv: http://arxiv.org/abs/2411.14971v1

Metric

Description

Grade Scale

Hallucination

Does the comment provide true information?

4: The comment provides only true information

3: The comment provides mostly true information

2: The comment provides mostly untrue information

1: The comment is completely untrue

Readability

Is the comment clear to read?

4: The comment is well-written

3: The comment has few problems

2: The comment has many problems

1: The comment is unreadable

Completeness

Does the comment address all capabilities of the relevant source code?

4: All essential functionality is documented

3: Most essential functionality is documented

2: Little essential functionality is documented

1: No essential functionality is documented

Usefulness

Is the comment useful?

4: The comment helps an expert programmer understand the code better

3: The comment helps an average programmer understand the code better

2: The comment documents only trivial functionality

1: The comment is not useful at any level