Chia-Yi Su

Chia-Yi Su, Collin McMillan

A code summary is a brief natural language description of source code. Summaries are usually only a single sentence long, and yet form the backbone of developer documentation. A short descriptions such as "changes all visible polygons to the color blue" can give a programmer a high-level idea of what code does without the effort of reading the code itself. Recently, products based on Large Language Models such as ChatGPT have demonstrated a strong ability to write these descriptions automatically. However, to use these tools, programmers must send their code to untrusted third parties for processing (e.g., via an API call). This loss of custody is not acceptable to many organizations. In this paper, we present an alternative: we train an open source model using sample output generated by GPT-3.5 in a process related to knowledge distillation. Our model is small enough (350m parameters) to be run on a single 16gb GPU, yet we show in our evaluation that it is large enough to mimic GPT-3.5 on this task.

Chia-Yi Su, Collin McMillan

This paper investigates code LLMs' capability of static analysis during code intelligence tasks such as code summarization and generation. Code LLMs are now household names for their abilities to do some programming tasks that have heretofore required people. The process that people follow to do programming tasks has long been understood to require static analysis. For example, human programmers navigate the call graph of large programs to comprehend the different parts of those programs. Education in programming includes static analysis under the assumption that better static analysis skills beget better programming. While popular culture is replete with anthropomorphic references such as LLM ``reasoning'', in fact code LLMs could exhibit a wholly alien thought process to humans. This paper studies the specific question of static analysis by code LLMs. We use three different static analysis tasks (callgraph generation, AST generation, and dataflow generation) and three different code intelligence tasks (code generation, summarization, and translation) with two different open-source models (Gemini and GPT-4o) and closed-source models (CodeLlaMA and Jam) as our experiments. We found that LLMs show poor performance on static analysis tasks and that pretraining on the static analysis tasks does not generalize to better performance on the code intelligence tasks and vice versa.

Chia-Yi Su, Collin McMillan

This paper presents a procedure for and evaluation of using a semantic similarity metric as a loss function for neural source code summarization. Code summarization is the task of writing natural language descriptions of source code. Neural code summarization refers to automated techniques for generating these descriptions using neural networks. Almost all current approaches involve neural networks as either standalone models or as part of a pretrained large language models e.g., GPT, Codex, LLaMA. Yet almost all also use a categorical cross-entropy (CCE) loss function for network optimization. Two problems with CCE are that 1) it computes loss over each word prediction one-at-a-time, rather than evaluating a whole sentence, and 2) it requires a perfect prediction, leaving no room for partial credit for synonyms. In this paper, we extend our previous work on semantic similarity metrics to show a procedure for using semantic similarity as a loss function to alleviate this problem, and we evaluate this procedure in several settings in both metrics-driven and human studies. In essence, we propose to use a semantic similarity metric to calculate loss over the whole output sentence prediction per training batch, rather than just loss for each word. We also propose to combine our loss with CCE for each word, which streamlines the training process compared to baselines. We evaluate our approach over several baselines and report improvement in the vast majority of conditions.

Aakash Bansal, Chia-Yi Su, Collin McMillan

Source code summarization is the task of writing natural language descriptions of source code. A typical use case is generating short summaries of subroutines for use in API documentation. The heart of almost all current research into code summarization is the encoder-decoder neural architecture, and the encoder input is almost always a single subroutine or other short code snippet. The problem with this setup is that the information needed to describe the code is often not present in the code itself -- that information often resides in other nearby code. In this paper, we revisit the idea of ``file context'' for code summarization. File context is the idea of encoding select information from other subroutines in the same file. We propose a novel modification of the Transformer architecture that is purpose-built to encode file context and demonstrate its improvement over several baselines. We find that file context helps on a subset of challenging examples where traditional approaches struggle.

Chia-Yi Su, Aakash Bansal, Vijayanta Jain et al.

This tool demonstration presents a research toolkit for a language model of Java source code. The target audience includes researchers studying problems at the granularity level of subroutines, statements, or variables in Java. In contrast to many existing language models, we prioritize features for researchers including an open and easily-searchable training set, a held out test set with different levels of deduplication from the training set, infrastructure for deduplicating new examples, and an implementation platform suitable for execution on equipment accessible to a relatively modest budget. Our model is a GPT2-like architecture with 350m parameters. Our training set includes 52m Java methods (9b tokens) and 13m StackOverflow threads (10.5b tokens). To improve accessibility of research to more members of the community, we limit local resource requirements to GPUs with 16GB video memory. We provide a test set of held out Java methods that include descriptive comments, including the entire Java projects for those methods. We also provide deduplication tools using precomputed hash tables at various similarity thresholds to help researchers ensure that their own test examples are not in the training set. We make all our tools and data open source and available via Huggingface and Github.

Maria Dhakal, Chia-Yi Su, Robert Wallace et al.

This paper describes an approach to improve code comments along different quality axes by rewriting those comments with customized Artificial Intelligence (AI)-based tools. We conduct an empirical study followed by grounded theory qualitative analysis to determine the quality axes to improve. Then we propose a procedure using a Large Language Model (LLM) to rewrite existing code comments along the quality axes. We implement our procedure using GPT-4o, then distil the results into a smaller model capable of being run in-house, so users can maintain data custody. We evaluate both our approach using GPT-4o and the distilled model versions. We show in an evaluation how our procedure improves code comments along the quality axes. We release all data and source code in an online repository for reproducibility.