Ακαδημαϊκές δημοσιεύσεις

ArXiv

YATE: The Role of Test Repair in LLM-Based Unit Test Generation

box_plot_line_branch_gnu
Συντάκτες: Michael Konstantinou, Renzo Degiovanni, Jie M. Zhang, Mark Harman, Mike Papadakis
Περίληψη:

Recent advances in automated test generation utilises language models to produce unit tests. While effective, language models tend to generate many incorrect tests with respect to both syntax and semantics. Although such incorrect tests can be easily detected and discarded, they constitute a "missed opportunity" -- if fixed, they are often valuable as they directly add testing value (they effectively target the underlying program logic to be tested) and indirectly form good seeds for generating additional tests. To this end, we propose a simple technique for repairing some of these incorrect tests through a combination of rule-based static analysis and re-prompting. We evaluate this simple approach, named YATE, on a set of 6 open-source projects and show that it can effectively produce tests that cover on average 32.06% more lines and kill 21.77% more mutants than a plain LLM-based method. We also compare YATE with four other LLM-based methods, namely HITS, SYMPROMPT, TESTSPARK and COVERUP and show that it produces tests that cover substantially more code. YATE achieves 22% higher line coverage, 20% higher branch coverage and kill 20% more mutants at a comparable cost (number of calls to LLMs). 

Διαβάστε περισσότερα :  Σύνδεσμος

ArXiv

Do LLMs generate test oracles that capture the actual or the expected program behaviour?

diff_actual_wrong
Συντάκτες: Michael Konstantinou, Renzo Degiovanni, Mike Papadakis
Περίληψη:

Software testing is an essential part of the software development cycle to improve the code quality. Typically, a unit test consists of a test prefix and a test oracle which captures the developer's intended behaviour. A known limitation of traditional test generation techniques (e.g. Randoop and Evosuite) is that they produce test oracles that capture the actual program behaviour rather than the expected one. Recent approaches leverage Large Language Models (LLMs), trained on an enormous amount of data, to generate developer-like code and test cases. We investigate whether the LLM-generated test oracles capture the actual or expected software behaviour. We thus, conduct a controlled experiment to answer this question, by studying LLMs performance on two tasks, namely, test oracle classification and generation. The study includes developer-written and automatically generated test cases and oracles for 24 open-source Java repositories, and different well tested prompts. Our findings show that LLM-based test generation approaches are also prone on generating oracles that capture the actual program behaviour rather than the expected one. Moreover, LLMs are better at generating test oracles rather than classifying the correct ones, and can generate better test oracles when the code contains meaningful test or variable names. Finally, LLM-generated test oracles have higher fault detection potential than the Evosuite ones. 

Integrative Zoology, January 2025.

A Novel Multidisciplinary Approach for Reptile Movement and Behavior Analysis

inz212960-fig-0004-m
Συντάκτες: Savvas Zotos, Marilena Stamatiou, Sofia-Zacharenia Marketaki, Michael Konstantinou, Andreas Aristidou, Duncan J. Irschick, Jeremy A. Bot, Emily L. C. Shepard, Mark D. Holton, Ioannis N. Vogiatzakis
Περίληψη:

The study of animals’ activity and behavior in the wild is an extremely challenging task. Although tri-axial accelerometers are invaluable for behavioral analyses, their use is more frequent in large charismatic endotherms with limited application in ectotherms. The scarce utilization of this methodology on small-size reptiles is focused on animals’ activity and energetics, showing few records of rapid displays and behavior signals. Here, we present a novel multidisciplinary approach capable of advancing research on reptiles’ behavior. Our proposed approach uses advanced technologies for the digitization, reconstruction and visualization of reptiles and their behavior. We (i) record movement through tri-axial accelerometers, video cameras, and motion capture systems; (ii) ground-truth data through the video records; (iii) develop realistically accurate 3D avatars of the recorded movement for visualization purposes, and (iv) archive data on a Behavior Pattern Database. As case studies, we used two small Mediterranean reptiles, the lizard Laudakia cypriaca and the snake Dolichophis jugularis. Through our approach, we successfully recorded, ground-truthed, and labeled for the first time, several detailed movements and behaviors of the two case study species. We developed an accurate digital overview of those movements using motion capture and 3D animal reconstruction. Finally, we structured a database for archiving all behavioral data and demonstrated how those archives can be used for advancing behavioral research, providing ecological insights into this animal group. Our approach can enhance research on reptiles’ behavior by contributing to the analysis of complex or isolated behaviors, poorly studied, such as signals and social interactions, providing valuable insights and assisting behavioral analysis.

Διαβάστε περισσότερα :  Σύνδεσμος

IEEE Computer Graphics and Applications, May 2022

Digitizing Wildlife: The case of reptiles 3D virtual museum

ReptilesVR___preview_600_450
Συντάκτες: Savvas Zotos, Marilena Lemonari, Michael Konstantinou, Anastasios Yiannakidis, Georgios Pappas, Panayiotis Kyriakou, Ioannis N. Vogiatzakis, Andreas Aristidou.
Περίληψη:

In this paper we design and develop a 3D virtual museum with holistic metadata documentation and a variety of reptile behaviors and movements. First, we reconstruct the reptiles mesh in high resolution, and then create its rigged/skinned digital counterpart. We acquire the movement of two subjects using an optical motion capture system, accelerometers, and RGB-vision cameras; these movements are then segmented and annotated to various behaviors. The 3D environment, VR and AR functionalities of our online repository serve as tools for interactively educating the public on animals, which are difficult to observe and study in their natural environment. It also reveals important information regarding animals' intangible characteristics (e.g., behavior), that is critical for the preservation of wildlife. Our museum is publicly accessible, enabling motion data reusability, and facilitating learning applications through gamification. We conducted a user study that confirms the naturalness and realism of our reptiles, along with the ease of use and usefulness of our museum.

Διαβάστε περισσότερα :  Σύνδεσμος