Related papers: Learning migration models for supporting increment…
We propose a modular architecture of language-specific encoder-decoders that constitutes a multilingual machine translation system that can be incrementally extended to new languages without the need for retraining the existing system when…
This paper addresses the limited transfer and adaptation capabilities of large language models in low-resource language scenarios. It proposes a unified framework that combines a knowledge transfer module with parameter-efficient…
Developers heavily rely on Application Programming Interfaces (APIs) from libraries to build their software. As software evolves, developers may need to replace the used libraries with alternate libraries, a process known as library…
Android is nowadays the most popular operating system in the world, not only in the realm of mobile devices, but also when considering desktop and laptop computers. Such a popularity makes it an attractive target for security attacks, also…
On-device deployment of Large Language Models (LLMs) frequently leverages Low-Rank Adapters (LoRAs) to support diverse downstream tasks under tight resource constraints. To address the limited storage capacity of mobile devices, recent…
Large Language Models (LLMs) are increasingly integrated into diverse applications. The rapid evolution of LLMs presents opportunities for developers to enhance applications continuously. However, this constant adaptation can also lead to…
Multilingual large language models (LLMs) possess impressive multilingual understanding and generation capabilities. However, their performance and cross-lingual alignment often lag for non-dominant languages. A common solution is to…
Patch backporting, the process of migrating mainline security patches to older branches, is an essential task in maintaining popular open-source projects (e.g., Linux kernel). However, manual backporting can be labor-intensive, while…
The importance of recommender systems is growing rapidly due to the exponential increase in the volume of content generated daily. This surge in content presents unique challenges for designing effective recommender systems. Key among these…
We propose to cast the task of morphological inflection - mapping a lemma to an indicated inflected form - for resource-poor languages as a meta-learning problem. Treating each language as a separate task, we use data from high-resource…
When modernizing a legacy application, it is easy to fall back on a like-for-like replica with new tools and updated design stylings, but this is an opportunity to explore making a more intuitive application that supports user tasks and…
Android apps require permissions when accessing resources related to privacy or system integrity. Starting from Android 6, these permissions have to be asked at runtime. However, migrating to the new permission model poses multiple…
Context: During the last years, developers of mobile applications have the possibility to use new paradigms and tools for developing mobile applications. For instance, since 2017 Android developers have the official support to write Android…
Software engineering activities such as package migration, fixing errors reports from static analysis or testing, and adding type annotations or other specifications to a codebase, involve pervasively editing the entire repository of code.…
Large Language Models (LLMs) are increasingly embedded in applications, and people can shape model behavior by editing prompt instructions. Yet encoding subtle, domain-specific policies into prompts is challenging. Although this process…
This paper focuses on extending the success of large language models (LLMs) to sequential decision making. Existing efforts either (i) re-train or finetune LLMs for decision making, or (ii) design prompts for pretrained LLMs. The former…
The adoption of Large Language Models (LLMs) is reshaping software development as developers integrate these LLMs into their applications. In such applications, prompts serve as the primary means of interacting with LLMs. Despite the…
Effective model-driven engineering of complex systems requires to appropriately describe different specific system aspects. To this end, efficient integration of different heterogeneous modeling languages is essential. Modeling language…
Model merging, such as model souping, is the practice of combining different models with the same architecture together without further training. In this work, we present a model merging methodology that addresses the difficulty of…
In this work, we investigate methods for the challenging task of translating between low-resource language pairs that exhibit some level of similarity. In particular, we consider the utility of transfer learning for translating between…