Related papers: From Commit Message Generation to History-Aware Co…

Large Language Models (LLMs) have demonstrated impressive capabilities in code completion tasks, where they assist developers by predicting and generating new code in real-time. However, existing LLM-based code completion systems primarily…

The availability of open-source projects facilitates developers to contribute and collaborate on a wide range of projects. As a result, the developer community contributing to such open-source projects is also increasing. Many of the…

The rapid evolution of LLMs represents an impactful paradigm shift in digital interaction and content engagement. While they encode vast amounts of human-generated knowledge and excel in processing diverse data types, they often face the…

Recently, dataset-generation-based zero-shot learning has shown promising results by training a task-specific model with a dataset synthesized from large pre-trained language models (PLMs). The final task-specific model often achieves…

Large Language Models (LLMs) are gaining popularity among software engineers. A crucial aspect of developing effective code generation LLMs is to evaluate these models using a robust benchmark. Evaluation benchmarks with quality issues can…

Current multimodal machine translation (MMT) systems rely on fully supervised data (i.e models are trained on sentences with their translations and accompanying images). However, this type of data is costly to collect, limiting the…

Creative writing is hard: Novelists struggle with writer's block daily. While automatic story generation has advanced recently, it is treated as a "toy task" for advancing artificial intelligence rather than helping people. In this paper,…

This paper presents a comprehensive evaluation of the code generation capabilities of ChatGPT, a prominent large language model, compared to human programmers. A novel dataset of 131 code-generation prompts across 5 categories was curated…

In the rapidly evolving industry of software development, coding efficiency and accuracy play significant roles in delivering high-quality software. Various code suggestion and completion tools, such as CodeBERT from Microsoft and GPT-3.5…

Research into methods for improving the performance of large language models (LLMs) through fine-tuning, retrieval-augmented generation (RAG) and soft-prompting has tended to focus on the use of highly technical or high-cost techniques,…

Large language models (LLMs) have been widely employed for graph-to-text generation tasks. However, the process of finetuning LLMs requires significant training resources and annotation work. In this paper, we explore the capability of…

Story generation is a challenging task, which demands to maintain consistency of the plots and characters throughout the story. Previous works have shown that GPT2, a large-scale language model, has achieved good performance on story…

Large pre-trained language models (LMs) such as GPT-3 have acquired a surprising ability to perform zero-shot learning. For example, to classify sentiment without any training examples, we can "prompt" the LM with the review and the label…

Alignment with human preferences is an important step in developing accurate and safe large language models. This is no exception in machine translation (MT), where better handling of language nuances and context-specific variations leads…

Generative Pre-trained Transformer (GPT) is a state-of-the-art machine learning model capable of generating human-like text through natural language processing (NLP). GPT is trained on massive amounts of text data and uses deep learning…

Providing effective feedback is important for student learning in programming problem-solving. In this sense, Large Language Models (LLMs) have emerged as potential tools to automate feedback generation. However, their reliability and…

Since the release of ChatGPT, generative models have achieved tremendous success and become the de facto approach for various NLP tasks. However, its application in the field of input methods remains under-explored. Many neural network…

The rapid advancements in large language models (LLMs) have greatly expanded the potential for automated code-related tasks. Two primary methodologies are used in this domain: prompt engineering and fine-tuning. Prompt engineering involves…

Code completion is widely used by software developers to provide coding suggestions given a partially written code snippet. Apart from the traditional code completion methods, which only support single token completion at minimal positions,…

Ever since Large Language Models (LLMs) and related applications have become broadly available, several studies investigated their potential for assisting educators and supporting students in higher education. LLMs such as Codex, GPT-3.5,…