English
Related papers

Related papers: Scaling Up Models and Data with $\texttt{t5x}$ and…

200 papers

Mainstream Transformer-based large language models face major efficiency bottlenecks: training computation scales quadratically with sequence length, and inference memory grows linearly, limiting long-context processing. Building large…

Recent studies have adopted pre-trained language models, such as CodeT5 and CodeGPT, for automated program generation tasks like code generation, repair, and translation. Numerous language model-based approaches have been proposed and…

Software Engineering · Computer Science 2024-01-09 Yue Liu , Chakkrit Tantithamthavorn , Yonghui Liu , Li Li

In this work we explore recent advances in instruction-tuning language models on a range of open instruction-following datasets. Despite recent claims that open models can be on par with state-of-the-art proprietary models, these claims are…

Scaling language models with more data, compute and parameters has driven significant progress in natural language processing. For example, thanks to scaling, GPT-3 was able to achieve strong results on in-context learning tasks. However,…

Large language models (LLMs) have garnered significant attention in both the AI community and beyond. Among these, the Generative Pre-trained Transformer (GPT) has emerged as the dominant architecture, spawning numerous variants. However,…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-02-02 Junqi Yin , Avishek Bose , Guojing Cong , Isaac Lyngaas , Quentin Anthony

For many new application domains for data-to-text generation, the main obstacle in training neural models consists of a lack of training data. While usually large numbers of instances are available on the data side, often only very few text…

Computation and Language · Computer Science 2021-02-09 Ernie Chang , Xiaoyu Shen , Dawei Zhu , Vera Demberg , Hui Su

Despite the recent success of multi-task learning and transfer learning for natural language processing (NLP), few works have systematically studied the effect of scaling up the number of tasks during pre-training. Towards this goal, this…

A common training approach for language models involves using a large-scale language model to expand a human-provided dataset, which is subsequently used for model training.This method significantly reduces training costs by eliminating the…

Computation and Language · Computer Science 2025-07-09 Minghang Zhu , Shen Gao , Zhengliang Shi , Jiabao Fang , Pengjie Ren , Zhaochun Ren , Zhumin Chen , Shuo Shang

General Large Language Models (LLMs) excel in reasoning, but those enhanced for translation struggle with reasoning tasks. To address this, we propose a novel translationenhanced recipe that begins with instruct models and applies…

Computation and Language · Computer Science 2025-10-13 Changjiang Gao , Zixian Huang , Jingyang Gong , Shujian Huang , Lei Li , Fei Yuan

Despite the huge success of Large Language Models (LLMs) in coding assistants like GitHub Copilot, these models struggle to understand the context present in the repository (e.g., imports, parent classes, files with similar names, etc.),…

Machine Learning · Computer Science 2023-06-21 Disha Shrivastava , Denis Kocetkov , Harm de Vries , Dzmitry Bahdanau , Torsten Scholak

Large language models (LLMs) are routinely pre-trained on billions of tokens, only to start the process over again once new data becomes available. A much more efficient solution is to continually pre-train these models, saving significant…

Unlike major Western languages, most African languages are very low-resourced. Furthermore, the resources that do exist are often scattered and difficult to obtain and discover. As a result, the data and code for existing research has…

Computation and Language · Computer Science 2019-06-26 Laura Martinus , Jade Z. Abbott

Well-trained machine-learning models, which leverage large amounts of open-source software data, have now become an interesting approach to automating many software engineering tasks. Several SE tasks have all been subject to this approach,…

Software Engineering · Computer Science 2022-02-04 Toufique Ahmed , Premkumar Devanbu

Large language models (LLMs) have rapidly advanced natural language processing, driving significant breakthroughs in tasks such as text generation, machine translation, and domain-specific reasoning. The field now faces a critical dilemma…

Computation and Language · Computer Science 2025-10-15 Jiya Manchanda , Laura Boettcher , Matheus Westphalen , Jasser Jasser

Instruction tuning is essential for Large Language Models (LLMs) to effectively follow user instructions. To improve training efficiency and reduce data redundancy, recent works use LLM-based scoring functions, e.g., Instruction-Following…

Machine Learning · Computer Science 2025-12-02 Yanjun Fu , Faisal Hamman , Sanghamitra Dutta

With the capabilities of understanding and executing natural language instructions, Large language models (LLMs) can potentially act as a powerful tool for textual data augmentation. However, the quality of augmented data depends heavily on…

Computation and Language · Computer Science 2024-04-30 Yichuan Li , Kaize Ding , Jianling Wang , Kyumin Lee

Instruction-tuning language models has become a crucial step in aligning them for general use. Typically, this process involves extensive training on large datasets, incurring high training costs. In this paper, we introduce a novel…

Computation and Language · Computer Science 2024-02-19 Dheeraj Mekala , Alex Nguyen , Jingbo Shang

Program optimization is the process of modifying software to execute more efficiently. Superoptimizers attempt to find the optimal program by employing significantly more expensive search and constraint solving techniques. Generally, these…

Machine Learning · Computer Science 2022-04-06 Alex Shypula , Pengcheng Yin , Jeremy Lacomis , Claire Le Goues , Edward Schwartz , Graham Neubig

Code generation is a longstanding challenge, aiming to generate a code snippet based on a natural language description. Usually, expensive text-code paired data is essential for training a code generation model. Recently, thanks to the…

Software Engineering · Computer Science 2022-06-15 Daoguang Zan , Bei Chen , Dejian Yang , Zeqi Lin , Minsu Kim , Bei Guan , Yongji Wang , Weizhu Chen , Jian-Guang Lou

Using large language models (LLMs) for source code has recently gained attention. LLMs, such as Transformer-based models like Codex and ChatGPT, have been shown to be highly capable of solving a wide range of programming problems. However,…

Computation and Language · Computer Science 2023-06-27 Atsushi Shirafuji , Yutaka Watanobe , Takumi Ito , Makoto Morishita , Yuki Nakamura , Yusuke Oda , Jun Suzuki