Issue reports have been recognized to contain rich information for retrieval-augmented code comment generation.However, how to minimize hallucinations in the generated comments remains significant challenges.In this paper, we propose IsComment, an issue-based LLM retrieval and verification approach for generating method's design rationale, usage directives, and so on as supplementary code comments.We first identify five main types of code supplementary information that issue reports can provide through code-comment-issue analysis.Next, we retrieve issue sentences containing these types of supplementary information and generate candidate code comments.To reduce hallucinations, we filter out those candidate comments that are irrelevant to the code or unverifiable by the issue report, making the code comment generation results more reliable.Our experiments indicate that compared with LLMs, IsComment increases the coverage of manual supplementary comments from 33.6% to 72.2% for ChatGPT, from 35.8% to 88.4% for GPT-4o, and from 35.0% to 86.2% for DeepSeek-V3.Compared with existing work, IsComment can generate richer and more useful supplementary code comments for programming understanding, which is quantitatively evaluated through the MESIA metric on both methods with and without manual code comments.

Existing code summarization approaches overlook developers' discriminative context focuses when generating code comments. This paper proposes a context-focused code sum-marization approach based on the prompt tuning technique. It enables the pre-trained code models to identify specific context focuses around a method and to generate the method's comment with corresponding contextual information, which improves the accuracy and informativeness of the generated comments. As the first attempt, we design prompt templates for six common types of contexts, construct a context-focused code-comment dataset, and prompt-tune two pre-trained code models with the dataset to generate code comments. The experimental results demonstrate that our approach significantly improves the existing models to generate context-focused comments. Compared with existing approaches, our generated comments are more informative, and our models can adapt to different code contexts, making the generation process more interpretable. We discuss the envisioned application of our approach and challenges for future work to tackle, including identifying more essential code contexts automatically, constructing more effective prompts, etc.

Code comments are important for developers in program comprehension. In scenarios of comprehending and reusing a method, developers expect code comments to provide supplementary information beyond the method signature. However, the extent of such supplementary information varies a lot in different code comments. In this paper, we raise the awareness of the supplementary nature of method-level comments and propose a new metric named MESIA (Mean Supplementary Information Amount) to assess the extent of supplementary information that a code comment can provide. With the MESIA metric, we conduct experiments on a popular code-comment dataset and three common types of neural approaches to generate method-level comments. Our experimental results demonstrate the value of our proposed work with a number of findings. (1) Small-MESIA comments occupy around 20% of the dataset and mostly fall into only the WHAT comment category. (2) Being able to provide various kinds of essential information, large-MESIA comments in the dataset are difficult for existing neural approaches to generate. (3) We can improve the capability of existing neural approaches to generate large-MESIA comments by reducing the proportion of small-MESIA comments in the training set. (4) The retrained model can generate large-MESIA comments that convey essential meaningful supplementary information for methods in the small-MESIA test set, but will get a lower BLEU score in evaluation. These findings indicate that with good training data, auto-generated comments can sometimes even surpass human-written reference comments, and having no appropriate ground truth for evaluation is an issue that needs to be addressed by future work on automatic comment generation.