English
Related papers

Related papers: MathCoder: Seamless Code Integration in LLMs for E…

200 papers

Large language models (LLMs) have increasingly been applied to automatic programming code generation. This task can be viewed as a language generation task that bridges natural language, human knowledge, and programming logic. However, it…

Code generation is one of the tasks for which the use of Large Language Models is widely adopted and highly successful. Given this popularity, there are many benchmarks dedicated to code generation that can help select the best model.…

Software Engineering · Computer Science 2026-05-12 Joanna Szych , Anne Schwerk

Code data has been shown to enhance the reasoning capabilities of large language models (LLMs), but it remains unclear which aspects of code are most responsible. We investigate this question with a systematic, data-centric framework. We…

Computation and Language · Computer Science 2025-10-03 Abdul Waheed , Zhen Wu , Carolyn Rosé , Daphne Ippolito

Large language models (LLMs) have demonstrated remarkable capabilities in code generation across various domains. However, their effectiveness in generating simulation scripts for domain-specific environments like ns-3 remains…

Networking and Internet Architecture · Computer Science 2025-07-16 Tasnim Ahmed , Mirza Mohammad Azwad , Salimur Choudhury

Large language models (LLMs) can solve problems step-by-step. While this chain-of-thought (CoT) reasoning boosts LLMs' performance, it is unclear if LLMs \textit{know} when to use CoT and whether those CoT are always necessary to answer the…

Computation and Language · Computer Science 2024-03-21 Cheng-Han Chiang , Hung-yi Lee

With the increasing popularity of large language models (LLMs), reasoning on basic graph algorithm problems is an essential intermediate step in assessing their abilities to process and infer complex graph reasoning tasks. Existing methods…

Computation and Language · Computer Science 2024-08-27 Qiaolong Cai , Zhaowei Wang , Shizhe Diao , James Kwok , Yangqiu Song

Current compiler optimization reports often present complex, technical information that is difficult for programmers to interpret and act upon effectively. This paper assesses the capability of large language models (LLM) to understand…

Programming Languages · Computer Science 2025-06-16 Peter Pirkelbauer , Chunhua Liao

Code editing plays a vital role in software engineering, requiring developers to adjust existing code according to natural language instructions while keeping functionality intact and avoiding unnecessary modifications. However,…

Software Engineering · Computer Science 2025-10-08 Zekai Zhang , Mingwei Liu , Zhenxi Chen , Linxi Liang , Yuxuan Chen , Guangsheng Ou , Yanlin Wang , Dan Li , Xin Peng , Zibin Zheng

Understanding code represents a core ability needed for automating software development tasks. While foundation models like LLMs show impressive results across many software engineering challenges, the extent of their true semantic…

Software Engineering · Computer Science 2025-04-16 Serge Lionel Nikiema , Jordan Samhi , Abdoul Kader Kaboré , Jacques Klein , Tegawendé F. Bissyandé

In the rapidly evolving field of natural language processing, the translation of linguistic descriptions into mathematical formulation of optimization problems presents a formidable challenge, demanding intricate understanding and…

Computation and Language · Computer Science 2024-03-05 Tasnim Ahmed , Salimur Choudhury

Large reasoning models (LRMs) like OpenAI-o1 have shown impressive capabilities in natural language reasoning. However, these models frequently demonstrate inefficiencies or inaccuracies when tackling complex mathematical operations. While…

Computation and Language · Computer Science 2025-10-24 Chengpeng Li , Zhengyang Tang , Ziniu Li , Mingfeng Xue , Keqin Bao , Tian Ding , Ruoyu Sun , Benyou Wang , Xiang Wang , Junyang Lin , Dayiheng Liu

Large Language Models have shown prominent capabilities in generating functional code from natural language descriptions. However, a standardized way to evaluate these capabilities in an objective and unbiased manner is still to be found.…

Software Engineering · Computer Science 2024-10-23 Álvaro Barbero Jiménez

Generating code from a natural language using Large Language Models (LLMs) such as ChatGPT, seems groundbreaking. Yet, with more extensive use, it's evident that this approach has its own limitations. The inherent ambiguity of natural…

Software Engineering · Computer Science 2023-10-09 Ahmed R. Sadik , Sebastian Brulin , Markus Olhofer

We introduce SELF-DISCOVER, a general framework for LLMs to self-discover the task-intrinsic reasoning structures to tackle complex reasoning problems that are challenging for typical prompting methods. Core to the framework is a…

Artificial Intelligence · Computer Science 2024-02-07 Pei Zhou , Jay Pujara , Xiang Ren , Xinyun Chen , Heng-Tze Cheng , Quoc V. Le , Ed H. Chi , Denny Zhou , Swaroop Mishra , Huaixiu Steven Zheng

Decompilation aims to convert binary code to high-level source code, but traditional tools like Ghidra often produce results that are difficult to read and execute. Motivated by the advancements in Large Language Models (LLMs), we propose…

Programming Languages · Computer Science 2025-08-06 Hanzhuo Tan , Qi Luo , Jing Li , Yuqun Zhang

It has been suggested that large language models such as GPT-4 have acquired some form of understanding beyond the correlations among the words in text including some understanding of mathematics as well. Here, we perform a critical inquiry…

Machine Learning · Computer Science 2023-11-15 Roozbeh Yousefzadeh , Xuenan Cao

Code Large Language Models (Code LLMs), such as StarCoder, have demonstrated exceptional performance in code-related tasks. However, most existing models are solely pre-trained on extensive raw code data without instruction fine-tuning. In…

Computation and Language · Computer Science 2025-05-28 Ziyang Luo , Can Xu , Pu Zhao , Qingfeng Sun , Xiubo Geng , Wenxiang Hu , Chongyang Tao , Jing Ma , Qingwei Lin , Daxin Jiang

Previous studies have typically assumed that large language models are unable to accurately perform arithmetic operations, particularly multiplication of >8 digits, and operations involving decimals and fractions, without the use of…

Machine Learning · Computer Science 2023-09-13 Zhen Yang , Ming Ding , Qingsong Lv , Zhihuan Jiang , Zehai He , Yuyi Guo , Jinfeng Bai , Jie Tang

Trustworthy evaluation methods for code snippets play a crucial role in neural code generation. Traditional methods, which either rely on reference solutions or require executable test cases, have inherent limitation in flexibility and…

Software Engineering · Computer Science 2025-05-27 Guang Yang , Yu Zhou , Xiang Chen , Wei Zheng , Xing Hu , Xin Zhou , David Lo , Taolue Chen

Large Language Models (LLMs) have shown strong potential for code generation, yet they remain limited in private-library-oriented code generation, where the goal is to generate code using APIs from private libraries. Existing approaches…

Software Engineering · Computer Science 2026-03-30 Yitong Zhang , Chengze Li , Ruize Chen , Guowei Yang , Xiaoran Jia , Yijie Ren , Jia Li