English
Related papers

Related papers: How Do Your Code LLMs Perform? Empowering Code Ins…

200 papers

A significant amount of research is focused on developing and evaluating large language models for a variety of code synthesis tasks. These include synthesizing code from natural language, synthesizing tests from code, and synthesizing…

Large language model agents for data analysis typically generate and execute code directly on databases. However, when applied to sensitive data, this approach poses significant security risks. To address this issue, we propose a…

Computation and Language · Computer Science 2025-11-18 Karthikeyan K , Raghuveer Thirukovalluru , Bhuwan Dhingra , David Edwin Carlson

It is crucial for large language models (LLMs) to follow instructions that involve multiple constraints. However, it is an unexplored area to enhance LLMs' ability to follow soft constraints. To bridge the gap, we initially design a…

Computation and Language · Computer Science 2025-06-03 Qingyu Ren , Jie Zeng , Qianyu He , Jiaqing Liang , Yanghua Xiao , Weikang Zhou , Zeye Sun , Fei Yu

Data science plays a critical role in biomedical research, but it requires professionals with expertise in coding and medical data analysis. Large language models (LLMs) have shown great potential in supporting medical tasks and performing…

Artificial Intelligence · Computer Science 2025-04-10 Zifeng Wang , Benjamin Danek , Ziwei Yang , Zheng Chen , Jimeng Sun

Recent development of large language models (LLMs) for code like CodeX and CodeT5+ demonstrates tremendous promise in achieving code intelligence. Their ability of synthesizing code that completes a program for performing a pre-defined task…

Computation and Language · Computer Science 2023-10-10 Weimin Xiong , Yiwen Guo , Hao Chen

While large language models (LLMs) show promise in code generation, existing benchmarks neglect the flowchart-based code generation. To promote further research on flowchart-based code generation, this work presents Flow2Code, a novel…

Software Engineering · Computer Science 2025-06-04 Mengliang He , Jiayi Zeng , Yankai Jiang , Wei Zhang , Zeming Liu , Xiaoming Shi , Aimin Zhou

Code Large Language Models (Code LLMs) have excelled at tasks like code completion but often miss deeper semantics such as execution effects and dynamic states. This paper aims to bridge the gap between Code LLMs' reliance on static text…

Computation and Language · Computer Science 2024-11-04 Yangruibo Ding , Jinjun Peng , Marcus J. Min , Gail Kaiser , Junfeng Yang , Baishakhi Ray

Recent works have shown that by curating high quality and diverse instruction tuning datasets, we can significantly improve instruction-following capabilities. However, creating such datasets is difficult and most works rely on manual…

Computation and Language · Computer Science 2024-11-12 Alexander Bukharin , Shiyang Li , Zhengyang Wang , Jingfeng Yang , Bing Yin , Xian Li , Chao Zhang , Tuo Zhao , Haoming Jiang

With the decline of Moore's law, optimizing program performance has become a major focus of software research. However, high-level optimizations such as API and algorithm changes remain elusive due to the difficulty of understanding the…

LaTeX's precision and flexibility in typesetting have made it the gold standard for the preparation of scientific documentation. Large Language Models (LLMs) present a promising opportunity for researchers to produce publication-ready…

Computation and Language · Computer Science 2025-09-16 Sahil Kale , Vijaykant Nadadur

Instruction tuning plays a pivotal role in Code Large Language Models (Code LLMs) for the task of program synthesis. Presently, two dominant paradigms for collecting tuning data are natural-instruct (human-written) and self-instruct…

Computation and Language · Computer Science 2024-03-04 Xianzhen Luo , Qingfu Zhu , Zhiming Zhang , Xu Wang , Qing Yang , Dongliang Xu , Wanxiang Che

As Large Language Models (LLMs) are increasingly applied across various tasks, instruction tuning has emerged as a critical method for enhancing model performance. However, current data management strategies face substantial challenges in…

Computation and Language · Computer Science 2025-04-15 Yangning Li , Zihua Lan , Lv Qingsong , Yinghui Li , Hai-Tao Zheng

AI programming assistants have demonstrated a tendency to generate code containing basic security vulnerabilities. While developers are ultimately responsible for validating and reviewing such outputs, improving the inherent quality of…

Cryptography and Security · Computer Science 2025-11-14 Catherine Xia , Manar H. Alalfi

Code language models have emerged as useful tools for various programming tasks, yet they often struggle when it comes to complex ones. In this paper, we explore the potential of curriculum learning in enhancing the performance of these…

Machine Learning · Computer Science 2024-07-16 Marwa Naïr , Kamel Yamani , Lynda Said Lhadj , Riyadh Baghdadi

There is a consensus that instruction fine-tuning of LLMs requires high-quality data, but what are they? LIMA (NeurIPS 2023) and AlpaGasus (ICLR 2024) are state-of-the-art methods for selecting such high-quality examples, either via manual…

Computation and Language · Computer Science 2024-06-05 Hao Zhao , Maksym Andriushchenko , Francesco Croce , Nicolas Flammarion

Large Language Models (LLMs) are widely utilized in software engineering (SE) tasks, such as code generation and automated program repair. However, their reliance on extensive and often undisclosed pre-training datasets raises significant…

Software Engineering · Computer Science 2025-02-11 Xin Zhou , Martin Weyssow , Ratnadira Widyasari , Ting Zhang , Junda He , Yunbo Lyu , Jianming Chang , Beiqi Zhang , Dan Huang , David Lo

Vectorization via Single Instruction, Multiple Data (SIMD) architectures is a cornerstone of high-performance computing. To fully exploit hardware potential, developers often resort to explicit vectorization using intrinsics, as…

Computation and Language · Computer Science 2026-05-19 Shangzhan Li , Xinyu Yin , Xuanyu Jin , Ye He , Yuxin Zhou , Yuxuan Li , Xu Han , Wanxiang Che , Qi Shi , Ting Liu , Maosong Sun

The development of video large multimodal models (LMMs) has been hindered by the difficulty of curating large amounts of high-quality raw data from the web. To address this, we propose an alternative approach by creating a high-quality…

Computer Vision and Pattern Recognition · Computer Science 2025-08-04 Yuanhan Zhang , Jinming Wu , Wei Li , Bo Li , Zejun Ma , Ziwei Liu , Chunyuan Li

Instruction tuning has become a key technique for enhancing the performance of large language models, enabling them to better follow human prompts. However, low-resource languages such as Luxembourgish face severe limitations due to the…

Computation and Language · Computer Science 2025-10-09 Fred Philippy , Laura Bernardy , Siwen Guo , Jacques Klein , Tegawendé F. Bissyandé

Despite the commendable progress of recent LLM-based data synthesis methods, they face two limitations in generating table instruction tuning data. First, they can not thoroughly explore the vast input space of table understanding tasks,…

Computation and Language · Computer Science 2025-06-11 Mingyu Zheng , Zhifan Feng , Jia Wang , Lanrui Wang , Zheng Lin , Yang Hao , Weiping Wang