Related papers: On the synchronization between Hugging Face pre-tr…

Large language models (LLMs) have demonstrated notable proficiency in code generation, with numerous prior studies showing their promising capabilities in various development scenarios. However, these studies mainly provide evaluations in…

Transformer-based large language models (LLMs) have achieved strong performance across many natural language processing tasks. Nonetheless, their quadratic computational and memory requirements, particularly in self-attention layers, pose…

Large language models (LLMs) have been applied to a wide range of tasks, including text summarization, web navigation, and chatbots. They have benefitted from supervised fine-tuning (SFT) and reinforcement learning from human feedback…

Background: Log messages provide valuable information about the status of software systems. This information is provided in an unstructured fashion and automated approaches are applied to extract relevant parameters. To ease this process,…

Solving complicated AI tasks with different domains and modalities is a key step toward artificial general intelligence. While there are numerous AI models available for various domains and modalities, they cannot handle complicated AI…

Aligning large language models (LLMs) with human preferences has proven to drastically improve usability and has driven rapid adoption as demonstrated by ChatGPT. Alignment techniques such as supervised fine-tuning (SFT) and reinforcement…

Code commits in a version control system (e.g., Git) should be atomic, i.e., focused on a single goal, such as adding a feature or fixing a bug. In practice, however, developers often bundle multiple concerns into tangled commits, obscuring…

GitHub commits, which record the code changes with natural language messages for description, play a critical role for software developers to comprehend the software evolution. To promote the development of the open-source software…

Selecting suitable architecture parameters and training hyperparameters is essential for enhancing machine learning (ML) model performance. Several recent empirical studies conduct large-scale correlational analysis on neural networks (NNs)…

Pre-trained language models (PTLMs) have achieved great success and remarkable performance over a wide range of natural language processing (NLP) tasks. However, there are also growing concerns regarding the potential security issues in the…

Motivated by the remarkable progress of large language models (LLMs) in objective tasks like mathematics and coding, there is growing interest in their potential to simulate human behavior--a capability with profound implications for…

Automating software development processes through the orchestration of GitHub Action workflows has revolutionized the efficiency and agility of software delivery pipelines. This paper presents a detailed investigation into the use of Large…

A prominent achievement of natural language processing (NLP) is its ability to understand and generate meaningful human language. This capability relies on complex feedforward transformer block architectures pre-trained on large language…

Currently, over a thousand LLMs exist that are multi-purpose and are capable of performing real world tasks, including Q&A, text summarization, content generation, etc. However, accessibility, scale and reliability of free models prevents…

Continuous Integration (CI) is a cornerstone of modern collaborative software development, and numerous CI platforms are available. Differences in maintenance overhead, reliability, and integration depth with code-hosting platforms make…

The disruptive technology provided by large-scale pre-trained language models (LLMs) such as ChatGPT or GPT-4 has received significant attention in several application domains, often with an emphasis on high-level opportunities and…

The rise of capabilities expressed by large language models has been quickly followed by the integration of the same complex systems into application level logic. Algorithms, programs, systems, and companies are built around structured…

Effective evaluation of multi-hop tool use is critical for analyzing the understanding, reasoning, and function-calling capabilities of large language models (LLMs). However, progress has been hindered by a lack of reliable evaluation…

Fine-tuning large language models (LLMs) raises privacy concerns due to the risk of exposing sensitive training data. Federated learning (FL) mitigates this risk by keeping training samples on local devices, while facing the following…

Large Language Models (LLMs) are rapidly reshaping machine translation (MT), particularly by introducing instruction-following, in-context learning, and preference-based alignment into what has traditionally been a supervised…