arXiv subjects

Fabian C. Peña

Publications and source records attributed to Fabian C. Peña.

5 recordsLinked to original sources

arXiv2026

SELU: A Software Engineering Language Understanding Benchmark

Large Language Models (LLMs) have demonstrated remarkable capabilities in code understanding and generation. However, their effectiveness on non-code Software Engineering (SE) tasks remains underexplored. We present 'Software Engineering Language Understanding' (SELU), the first comprehensive benchmark for evaluating LLMs on 22 SE textual artifacts NLU tasks, spanning from identifying whether a requirement is functional or non-functional to estimating the effort required to implement a development task. SELU covers classification, regression, Named Entity Recognition (NER), and Masked Language Modeling (MLM) tasks, with data drawn from diverse sources such as issue tracking systems and developer forums. We fine-tune 22 open-source LLMs, both generalist and domain-adapted; and prompt two proprietary alternatives using zero-shot a 3-shot prompting strategies. Performance is measured using metrics such as F1-macro, SMAPE, F1-micro, and accuracy, and compared via the Bayesian signed-rank test. Our results show that fine-tuned models across various sizes and architectures perform best, exhibiting high mean performance and low across-task variance. Furthermore, domain adaptation via code-focused pre-training does not yield significant improvements and might even be counterproductive for developer communication tasks.

cs.SE↗

arXiv2026

Large Language Models Have Unreliable Understanding of Software Engineering Terminology

Large Language Models (LLMs) are increasingly used in software engineering (SE), yet there is no systematic study that determines to which degree these LLMs actually understand standardized SE terminology. Lack of such understanding can lead to miscommunication and misunderstanding, both by LLMs consuming text but also by human-developers acting on LLM-generated text. Within this paper, we investigate to which degree state-of-the-art LLMs are able to identify whether definitions from the ISO/IEC/IEEE 24765:2017 Systems and Software Engineering - Vocabulary are correct. We prompt LLMs both with correct definitions, as well as systematically falsified definitions. The falsifications are both semantic (substitution of key terms) and structural (removing critical information). We measure both classification accuracy and whether reasoning tokens generated by the LLMs make sense with respect to understanding the definition. While most LLMs detect falsified definitions with high accuracy, they also reject many correct definitions, indicating a systematic rejection bias rather than genuine discriminative understanding. Explicit reasoning does not consistently improve results and may even hinder performance through over-thinking. Our work demonstrates that while the performance of LLMs (including their agentic use) in many SE tasks is impressive, there are still fundamental issues to understand how this will impact SE, including the consistent use of terminology.

cs.SE↗

arXiv2026

Pre-Training on Software Engineering Texts: Effects on Domain Adaptation and General-Language Understanding

Generalist and code-focused Language Models (LMs) are increasingly applied to software engineering (SE), yet whether they are optimized for understanding SE textual artifacts (e.g., issues, commit messages, developer discussions) remains unclear, as most evidence comes from code-focused benchmarks. We study how to adapt encoder and decoder LMs to SE text, comparing continual pre-training (CPT) against pre-training from scratch (PTS) on a new SE corpus, and evaluating both domain adaptation (SELU) and general-language understanding (SuperGLUE). To keep the comparisons fair, we control pre-training under constant-token and compute-matched budgets. We find that across families and sizes, reusing an existing LM dominates training a domain-native one from scratch: CPT yields small and mostly inconclusive domain gains while leaving general-language understanding essentially unchanged, whereas PTS pays a large and usually decisive penalty on both axes and becomes competitive only for small LMs under a token-rich budget. We distill these results into practical guidance for adapting LMs to SE text and release our corpus and pre-trained LMs in our replication kit.

cs.SE↗

arXiv2025

Augmenting the Generality and Performance of Large Language Models for Software Engineering

Large Language Models (LLMs) are revolutionizing software engineering (SE), with special emphasis on code generation and analysis. However, their applications to broader SE practices including conceptualization, design, and other non-code tasks, remain partially underexplored. This research aims to augment the generality and performance of LLMs for SE by (1) advancing the understanding of how LLMs with different characteristics perform on various non-code tasks, (2) evaluating them as sources of foundational knowledge in SE, and (3) effectively detecting hallucinations on SE statements. The expected contributions include a variety of LLMs trained and evaluated on domain-specific datasets, new benchmarks on foundational knowledge in SE, and methods for detecting hallucinations. Initial results in terms of performance improvements on various non-code tasks are promising.

cs.SE↗

arXiv2025

Evaluating the Performance and Efficiency of Sentence-BERT for Code Comment Classification

This work evaluates Sentence-BERT for a multi-label code comment classification task seeking to maximize the classification performance while controlling efficiency constraints during inference. Using a dataset of 13,216 labeled comment sentences, Sentence-BERT models are fine-tuned and combined with different classification heads to recognize comment types. While larger models outperform smaller ones in terms of F1, the latter offer outstanding efficiency, both in runtime and GFLOPS. As result, a balance between a reasonable F1 improvement (+0.0346) and a minimal efficiency degradation (+1.4x in runtime and +2.1x in GFLOPS) is reached.

cs.SE↗