Search Results for author:
Found 27 papers, 14 papers with code
An Exploratory Investigation into Code License Infringements in Large Language Model Training Datasets
Based on the findings of our study, which highlights the pervasive issue of license inconsistencies in large language models trained on code, our recommendation for both researchers and the community is to prioritize the development and adoption of best practices for dataset creation and management.
Language Models for Code Completion: A Practical Evaluation
InCoder outperformed the other models across all programming languages, highlighting the significance of training data and objectives.
McUDI: Model-Centric Unsupervised Degradation Indicator for Failure Prediction AIOps Solutions
Due to the continuous change in operational data, AIOps solutions suffer from performance degradation over time.
Data vs. Model Machine Learning Fairness Testing: An Empirical Study
We find a linear relationship between data and model fairness metrics when the distribution and the size of the training data changes.
Traces of Memorisation in Large Language Models for Code
We find that large language models for code are vulnerable to data extraction attacks, like their natural language counterparts.
Faithful Model Explanations through Energy-Constrained Conformal Counterfactuals
We formalise this notion of faithfulness through the introduction of a tailored evaluation metric and propose a novel algorithmic framework for generating Energy-Constrained Conformal Counterfactuals that are only as plausible as the model permits.
Is Your Anomaly Detector Ready for Change? Adapting AIOps Solutions to the Real World
Anomaly detection techniques are essential in automating the monitoring of IT systems and operations.
On the Impact of Language Selection for Training and Evaluating Programming Language Models
The recent advancements in Transformer-based Language Models have demonstrated significant potential in enhancing the multilingual capabilities of these models.
Endogenous Macrodynamics in Algorithmic Recourse
Existing work on Counterfactual Explanations (CE) and Algorithmic Recourse (AR) has largely focused on single individuals in a static environment: given some estimated model, the goal is to find valid counterfactuals for an individual instance that fulfill various desiderata.
Explaining Black-Box Models through Counterfactuals
We present CounterfactualExplanations. jl: a package for generating Counterfactual Explanations (CE) and Algorithmic Recourse (AR) for black-box models in Julia.
Batching for Green AI -- An Exploratory Study on Inference
In this study, we examine the effect of input batching on the energy consumption and response times of five fully-trained neural networks for computer vision that were considered state-of-the-art at the time of their publication.
Enriching Source Code with Contextual Data for Code Completion Models: An Empirical Study
For comments, we find that the models perform better in the presence of multi-line comments (again with small effect sizes).
Uncovering Energy-Efficient Practices in Deep Learning Training: Preliminary Steps Towards Green AI
To expand the application of Green AI, we advocate for a shift in the design of deep learning models, by considering the trade-off between energy efficiency and accuracy.
STACC: Code Comment Classification using SentenceTransformers
Code comments are a key resource for information about software artefacts.
Targeted Attack on GPT-Neo for the SATML Language Model Data Extraction Challenge
In this work, we apply a targeted data extraction attack to the SATML2023 Language Model Training Data Extraction Challenge.
Extending Source Code Pre-Trained Language Models to Summarise Decompiled Binaries
While the automated summarisation of decompiled code can help Reverse Engineers understand and analyse binaries, current work mainly focuses on summarising source code, and no suitable dataset exists for this task.
Are Concept Drift Detectors Reliable Alarming Systems? -- A Comparative Study
We compare the performance of the most popular drift detectors belonging to two different concept drift detector groups, error rate-based detectors and data distribution-based detectors.
An Empirical Study on Data Leakage and Generalizability of Link Prediction Models for Issues and Commits
However, these approaches primarily focused on improving prediction accuracy on randomly-split datasets, with limited attention given to the impact of data leakage and the generalizability of the predictive models.
Code Smells for Machine Learning Applications
Hence ensuring code quality is quintessential to avoid issues in the long run.
Data Smells in Public Datasets
The adoption of Artificial Intelligence (AI) in high-stakes domains such as healthcare, wildlife preservation, autonomous driving and criminal justice system calls for a data-centric approach to AI.
Using Large-scale Heterogeneous Graph Representation Learning for Code Review Recommendations at Microsoft
Code review is an integral part of any mature software development process, and identifying the best reviewer for a code change is a well-accepted problem within the software engineering community.
"Project smells" -- Experiences in Analysing the Software Quality of ML Projects with mllint
We also investigate the perceived importance of these project smells for proof-of-concept versus production-ready ML projects, as well as the perceived obstructions and benefits to using static analysis tools such as mllint.
The Prevalence of Code Smells in Machine Learning projects
Manual analysis of these smells mainly showed that code duplication is widespread and that the PEP8 convention for identifier naming style may not always be applicable to ML code due to its resemblance with mathematical notation.
An Exploratory Study of Log Placement Recommendation in an Enterprise System
In this paper, we study the log placement problem in the code base of Adyen, a large-scale payment company.
ConE: A Concurrent Edit Detection Tool for Large Scale Software Development
We study half a year of changes made to six large repositories in Microsoft in which at least 1, 000 pull requests are created each month.
Nudge: Accelerating Overdue Pull Requests Towards Completion
The key novelty of Nudge is that it succeeds in reducing pull request resolution time, while ensuring that developers perceive the notifications sent as useful, at the scale of thousands of repositories.
AI Lifecycle Models Need To Be Revised. An Exploratory Study in Fintech
Thus, the same development processes and standards in software engineering ought to be complied in artificial intelligence systems.
Software Engineering 68T01 I.2.0; D.2.9
