The reliable application of deep learning models to software engineering tasks hinges on high-quality training data. Yet, large-scale repositories inevitably introduce noisy or mislabeled examples that degrade both accuracy and robustness. While Noise Label Learning (NLL) has been extensively studied in other fields, there are a few works that investigate NLL in Software Engineering (SE) and Large Language Models (LLMs) for SE tasks. In this work, we propose MANTRA, a Multi-stage Adaptive Noise TReAtment framework that embeds noise diagnosis and mitigation directly into the fine-tuning process of code-Pretrained Language Models (PTM) and code-LLMs. We first investigate the effect of noise at varying levels on convergence and loss trajectories of the models. Then we apply an adaptive dropout strategy guided by per-sample loss dynamics and Gaussian Mixture Model clustering to exclude persistently noisy points while preserving clean data. Applying to code summarization and commit intent classification, our experiments reveal that some LLMs are more sensitive to noise than others. However, with MANTRA, the performance of all models in both tasks is improved. MANTRA enables researchers and practitioners to reduce the impact of errors introduced by the dataset in training, saves time in data cleaning and processing, while maximizing the effect of fine-tuning.

Pre-trained language models (PLMs) are increasingly being applied to code-related tasks. Although PLMs have achieved good results, they do not take into account potential high-order data correlations within the code. We propose three types of high-order correlations in code tokens, i.e. abstract syntax tree family correlation, lexical correlation, and line correlation. We design a tokens and hyperedges generator to capture these high-order data correlations. We improve the architecture of hypergraph neural networks and combine it with adapter tuning to propose a novel hypergraph-based adapter (HGAdapter) to fine-tune PLMs. HGAdapter can encode high-order data correlations and is allowed to be inserted into various PLMs to enhance performance. Experiments were conducted on several public datasets, including six languages of code summarization and code clone detection tasks. Our methods improved the performance of PLMs in datasets to varying degrees. Experimental results validate the introduction of high-order data correlations that contribute to improved effectiveness.

This paper presents a multi-granularity method for source code summarization, which generates a concise functional description for the given code snippet. We notice that skilled programmers write and read source codes hierarchically and pay close attention to conceptual entities like statements, tokens, sub-tokens, and the mapping relations between them. The entities have specific emphasis according to their granularities, e.g., statements in coarse-granularity reveal the global logical semantics of code, and the sub-tokens in fine-granularity are more related to the textual semantics. Driven by this observation, we demonstrate that a multi-granularity formulation incorporating these conceptual entities benefit the code summarization task. Concretely, the source code is transformed into a pyramidal representation, and then a pyramid attention mechanism is applied for efficient feature aggregation among different hierarchies in it. We instantiate our multi-granularity method using the proposed pyramid attention and name it P A-former (Pyramid Attention transformer). We evaluated it on two source code summarization benchmarks where it surpasses the prior works and achieves new state-of-the-art results.

Unit tests often lack concise summaries that convey test intent, especially in auto-generated or poorly documented codebases. Large Language Models (LLMs) offer a promising solution, but their effectiveness depends heavily on how they are prompted. Unlike generic code summarization, test-code summarization poses distinct challenges because test methods validate expected behavior through assertions rather than implementing functionality. This paper presents a new benchmark of 91 real-world Java test cases paired with developer-written summaries and conducts a controlled ablation study to investigate how test code-related components-such as the method under test (MUT), assertion messages, and assertion semantics-affect the performance of LLM-generated test summaries. We evaluate four code LLMs (Codex, Codestral, DeepSeek, and Qwen-Coder) across seven prompt configurations using n-gram metrics (BLEU, ROUGE-L, METEOR), semantic similarity (BERTScore), and LLM-based evaluation. Results show that prompting with assertion semantics improves summary quality by an average of 0.10 points (2.3%) over full MUT context (4.45 vs. 4.35) while requiring fewer input tokens. Codex and Qwen-Coder achieve the highest alignment with human-written summaries, while DeepSeek underperforms despite high lexical overlap. The replication package is publicly available at https://doi.org/10. 5281/zenodo.17067550

Programming languages can benefit from one another by utilizing a language model for software engineering tasks. Full fine-tuning and Parameter Efficient Fine-Tuning (PEFT) of Code Language Models (Code-LMs) has been explored for multilingual knowledge transfer. AdapterFusion is a PEFT architecture that aims to enhance task performance by leveraging information from multiple programming languages, but primarily focuses on the target programming language. In our previous work, we proposed AdvFusion, a novel PEFT-based approach that effectively learns from other programming languages before adapting to the target task. Though previous experiments showed that AdvFusion outperformed AdapterFusion and LoRA, it was applied on pre-trained Code-LMs and was limited to only two tasks, code summarization and method name prediction. In this study, we expanded our work and investigated AdvFusion on Code Large Language Models (Code-LLMs), considering three new tasks: code generation, code translation, and commit message generation. We observed that different Code-LLMs/tasks exhibit different characteristics. In code generation, AdvFusion outperformed AdapterFusion but not other PEFT methods (LoRA, Compacter, and TaskAdapter). In commit message generation, AdapterFusion performed better than AdvFusion, and contrary to code generation, we found that the other PEFT methods do not have better performance. In code translation, AdvFusion performed worse than AdapterFusion overall, with the performance gap marginally widening as the model size increases. However, consistent with code generation, other PEFT methods showed better performance.

Large Language Models (LLMs) and other automated techniques have been increasingly used to support software developers by generating software artifacts such as code snippets, patches, and comments. However, accurately assessing the correctness of these generated artifacts remains a significant challenge. On one hand, human evaluation provides high accuracy but is labor-intensive and lacks scalability. On the other hand, many automatic evaluation metrics are scalable and require minimal human effort, but they often fail to accurately reflect the actual correctness of generated software artifacts. In this paper, we present SE-Jury, the first evaluation metric for LLM-as-Ensemble-Judge specifically designed to accurately assess the correctness of generated software artifacts. SE-Jury first defines five distinct evaluation strategies, each implemented by an independent judge. A dynamic team selection mechanism then identifies the most appropriate subset of judges as a team to produce a final correctness score through ensembling. We evaluate SE-Jury across a diverse set of software engineering (SE) benchmarks that span three popular SE tasks: code generation, automated program repair, and code summarization. Results demonstrate that SE-Jury consistently achieves a higher correlation with human judgments, with improvements ranging from 29.6% to 140.8% over existing automatic metrics. SE-Jury reaches agreement levels with human annotators that are close to inter-annotator agreement in code generation and program repair. These findings underscore SE-Jury's potential as a scalable and reliable alternative to human evaluation in these SE tasks.

User stories are essential in agile development, yet often missing or outdated in legacy and poorly documented systems. We investigate whether large language models (LLMs) can automatically recover user stories directly from source code and how prompt design impacts output quality. Using 1,750 annotated C++ snippets of varying complexity, we evaluate five state-of-the-art LLMs across six prompting strategies. Results show that all models achieve, on average, an F1 score of 0.8 for code up to 200 NLOC. Our findings show that a single illustrative example enables the smallest model (8B) to match the performance of a much larger 70B model. In contrast, structured reasoning via Chain-of-Thought offers only marginal gains, primarily for larger models.

This paper presents a multi-granularity method for source code summarization, which generates a concise functional description for the given code snippet. We notice that skilled programmers write and read source codes hierarchically and pay close attention to conceptual entities like statements, tokens, sub-tokens, and the mapping relations between them. The entities have specific emphasis according to their granularities, e.g., statements in coarse-granularity reveal the global logical semantics of code, and the sub-tokens in fine-granularity are more related to the textual semantics. Driven by this observation, we demonstrate that a multi-granularity formulation incorporating these conceptual entities benefit the code summarization task. Concretely, the source code is transformed into a pyramidal representation, and then a pyramid attention mechanism is applied for efficient feature aggregation among different hierarchies in it. We instantiate our multi-granularity method using the proposed pyramid attention and name it P A-former (Pyramid Attention transformer). We evaluated it on two source code summarization benchmarks where it surpasses the prior works and achieves new state-of-the-art results.

Profiling tools (also known as profilers) play an important role in understanding program performance at runtime, such as hotspots, bottlenecks, and inefficiencies. While profilers have been proven to be useful, they give extra burden to software engineers. Software engineers, as the users, are responsible to interpret the complex performance data and identify actionable optimization in program source code. However, it can be challenging for users to associate inefficiencies with the program semantics, especially if the users are not the authors of the code, which limits the applicability of profilers. In this thesis, we explore a new direction to combine performance profiles and program semantics with a deep learning approach. The key idea is to glean code summary for semantic information (at a certain level) and integrate it into a profiler, which can better understand program inefficiencies for actionable optimization. To be concrete, we combine profiles generated by Async Profiler (the state-of-the-art Java profiler) with code summarization from a fine-tuned CodeBERT-based model. We demonstrate the code summaries of any selected call path in a graphic user interface. Our system can effectively assist analysis on many Java benchmarks.

Large Language Models (LLMs) have become widely used across diverse NLP tasks and domains, demonstrating their adaptability and effectiveness. In the realm of Electronic Design Automation (EDA), LLMs show promise for tasks like Register-Transfer Level (RTL) code generation and summarization. However, despite the proliferation of LLMs for general code-related tasks, there's a dearth of research focused on evaluating and refining these models for hardware description languages (HDLs), notably VHDL. In this study, we evaluate the performance of existing code LLMs for VHDL code generation and summarization using various metrics and two datasets -- VHDL-Eval and VHDL-Xform. The latter, an in-house dataset, aims to gauge LLMs' understanding of functionally equivalent code. Our findings reveal consistent underperformance of these models across different metrics, underscoring a significant gap in their suitability for this domain. To address this challenge, we propose Chain-of-Descriptions (CoDes), a novel approach to enhance the performance of LLMs for VHDL code generation and summarization tasks. CoDes involves generating a series of intermediate descriptive steps based on: (i) the problem statement for code generation, and (ii) the VHDL code for summarization. These steps are then integrated with the original input prompt (problem statement or code) and provided as input to the LLMs to generate the final output. Our experiments demonstrate that the CoDes approach significantly surpasses the standard prompting strategy across various metrics on both datasets. This method not only improves the quality of VHDL code generation and summarization but also serves as a framework for future research aimed at enhancing code LLMs for VHDL.