English
Related papers

Related papers: CodeIt: Self-Improving Language Models with Priori…

200 papers

In practice, rigorous reasoning is often a key driver of correct code, while Reinforcement Learning (RL) for code generation often neglects optimizing reasoning quality. Bringing process-level supervision into RL is appealing, but it faces…

Software Engineering · Computer Science 2026-05-06 Lishui Fan , Yu Zhang , Mouxiang Chen , Zhongxin Liu

Code reasoning is a fundamental capability for large language models (LLMs) in the code domain. It involves understanding and predicting a program's execution behavior, such as determining the output for a given input or whether a specific…

Software Engineering · Computer Science 2025-07-24 Lingxiao Tang , He Ye , Zhongxin Liu , Xiaoxue Ren , Lingfeng Bao

Researchers have investigated the potential of leveraging pre-trained language models, such as CodeBERT, to enhance source code-related tasks. Previous methodologies have relied on CodeBERT's '[CLS]' token as the embedding representation of…

Computation and Language · Computer Science 2024-09-04 Yong Ma , Senlin Luo , Yu-Ming Shang , Yifei Zhang , Zhengjun Li

Although chain-of-thought (CoT) prompting combined with language models has achieved encouraging results on complex reasoning tasks, the naive greedy decoding used in CoT prompting usually causes the repetitiveness and local optimality. To…

Computation and Language · Computer Science 2024-05-27 Lei Lin , Jiayi Fu , Pengli Liu , Qingyang Li , Yan Gong , Junchen Wan , Fuzheng Zhang , Zhongyuan Wang , Di Zhang , Kun Gai

Code completion, which aims to predict the following code token(s) according to the code context, can improve the productivity of software development. Recent work has proved that statistical language modeling with transformers can greatly…

Software Engineering · Computer Science 2022-03-16 Shuai Lu , Nan Duan , Hojae Han , Daya Guo , Seung-won Hwang , Alexey Svyatkovskiy

Large language models make remarkable progress in reasoning capabilities. Existing works focus mainly on deductive reasoning tasks (e.g., code and math), while another type of reasoning mode that better aligns with human learning, inductive…

Computation and Language · Computer Science 2025-03-18 Kedi Chen , Zhikai Lei , Fan Zhang , Yinqi Zhang , Qin Chen , Jie Zhou , Liang He , Qipeng Guo , Kai Chen , Wei Zhang

Chain-of-Thought (CoT) reasoning has become a foundation for eliciting multi-step reasoning in large language models, but recent studies show that its benefits do not scale monotonically with chain length: while longer CoT generally enables…

Artificial Intelligence · Computer Science 2026-05-19 Bin Lei , Caiwen Ding , Jiachen Yang , Ang Li , Xin Eric Wang

Transformer based code models have impressive performance in many software engineering tasks. However, their effectiveness degrades when symbols are missing or not informative. The reason is that the model may not learn to pay attention to…

Software Engineering · Computer Science 2024-11-22 Zian Su , Xiangzhe Xu , Ziyang Huang , Zhuo Zhang , Yapeng Ye , Jianjun Huang , Xiangyu Zhang

We present four main contributions to enhance the performance of Large Language Models (LLMs) in generating domain-specific code: (i) utilizing LLM-based data splitting and data renovation techniques to improve the semantic representation…

Computation and Language · Computer Science 2024-01-31 Yu-Chen Lin , Akhilesh Kumar , Norman Chang , Wenliang Zhang , Muhammad Zakir , Rucha Apte , Haiyang He , Chao Wang , Jyh-Shing Roger Jang

AI researchers and practitioners increasingly apply large language models (LLMs) to what we call reasoning-intensive regression (RiR), i.e., deducing subtle numerical scores from text. Unlike standard language regression tasks such as…

Computation and Language · Computer Science 2026-05-04 Diane Tchuindjo , Omar Khattab

Large Language Models (LLMs) have recently advanced many applications on software engineering tasks, particularly the potential for code generation. Among contemporary challenges, code generated by LLMs often suffers from inaccuracies and…

Software Engineering · Computer Science 2024-08-29 Thai Tang Quoc , Duc Ha Minh , Tho Quan Thanh , Anh Nguyen-Duc

Scaling inference-time computation has substantially improved the reasoning capabilities of language models. However, existing methods have significant limitations: serialized chain-of-thought approaches generate overly long outputs,…

Artificial Intelligence · Computer Science 2025-08-19 Jiayi Pan , Xiuyu Li , Long Lian , Charlie Snell , Yifei Zhou , Adam Yala , Trevor Darrell , Kurt Keutzer , Alane Suhr

Large language models exhibit strong reasoning capabilities, yet often rely on shortcuts such as surface pattern matching and answer memorization rather than genuine logical inference. We propose Shortcut-Aware Reasoning Training (SART), a…

Computation and Language · Computer Science 2026-03-24 Hongyu Cao , Kunpeng Liu , Dongjie Wang , Yanjie Fu

In recent research advancements within the community, large language models (LLMs) have sparked great interest in creating autonomous agents. However, current prompt-based agents often heavily rely on large-scale LLMs. Meanwhile, although…

Computation and Language · Computer Science 2025-03-04 Xueyang Feng , Bo Lan , Quanyu Dai , Lei Wang , Jiakai Tang , Xu Chen , Zhenhua Dong , Ji-Rong Wen

Much of software-engineering research relies on the naturalness of code, the fact that code, in small code snippets, is repetitive and can be predicted using statistical language models like n-gram. Although powerful, training such models…

Software Engineering · Computer Science 2022-08-15 Ahmed Khanfir , Matthieu Jimenez , Mike Papadakis , Yves Le Traon

Large language models (LLMs) have shown great potential in code-related tasks, yet open-source models lag behind their closed-source counterparts. To bridge this performance gap, existing methods generate vast amounts of synthetic data for…

Computation and Language · Computer Science 2024-08-06 Weijie Lv , Xuan Xia , Sheng-Jun Huang

Existing large language models (LLMs) face challenges of following complex instructions, especially when multiple constraints are present and organized in paralleling, chaining, and branching structures. One intuitive solution, namely…

Computer Vision and Pattern Recognition · Computer Science 2025-10-01 Yulei Qin , Gang Li , Zongyi Li , Zihan Xu , Yuchen Shi , Zhekai Lin , Xiao Cui , Ke Li , Xing Sun

Building on recent advances in language-based reasoning models, we explore multimodal reasoning that integrates vision and text. Existing multimodal benchmarks primarily test visual extraction combined with text-based reasoning, lacking…

Computer Vision and Pattern Recognition · Computer Science 2025-06-16 Mert Unsal , Aylin Akkus

While artificial intelligence (AI) models have achieved human or even superhuman performance in many well-defined applications, they still struggle to show signs of broad and flexible intelligence. The Abstraction and Reasoning Corpus…

Artificial Intelligence · Computer Science 2023-06-23 Giacomo Camposampiero , Loic Houmard , Benjamin Estermann , Joël Mathys , Roger Wattenhofer

Large language models (LLMs) can achieve highly effective performance on various reasoning tasks by incorporating step-by-step chain-of-thought (CoT) prompting as demonstrations. However, the reasoning chains of demonstrations generated by…

Computation and Language · Computer Science 2024-03-18 Jiashuo Sun , Yi Luo , Yeyun Gong , Chen Lin , Yelong Shen , Jian Guo , Nan Duan