English
Related papers

Related papers: The Devil is in the Tails: How Long-Tailed Code Di…

200 papers

Output-length prediction is important for efficient LLM serving, as it directly affects batching, memory reservation, and scheduling. For prompt-only length prediction, most existing methods use a one-shot sampled length as the label,…

Machine Learning · Computer Science 2026-04-10 Jing Wang , Yu-Yang Qian , Ke Xue , Chao Qian , Peng Zhao , Zhi-Hua Zhou

This paper considers learning deep features from long-tailed data. We observe that in the deep feature space, the head classes and the tail classes present different distribution patterns. The head classes have a relatively large spatial…

Computer Vision and Pattern Recognition · Computer Science 2020-04-14 Jialun Liu , Yifan Sun , Chuchu Han , Zhaopeng Dou , Wenhui Li

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

Reinforcement learning(RL) post-training has become essential for aligning large language models (LLMs), yet its efficiency is increasingly constrained by the rollout phase, where long trajectories are generated token by token. We identify…

Large Language Models (LLMs) have shown capabilities close to human performance in various analytical tasks, leading researchers to use them for time and labor-intensive analyses. However, their capability to handle highly specialized and…

Computation and Language · Computer Science 2024-10-08 Alexander S. Choi , Syeda Sabrina Akter , JP Singh , Antonios Anastasopoulos

We propose a simple data model inspired from natural data such as text or images, and use it to study the importance of learning features in order to achieve good generalization. Our data model follows a long-tailed distribution in the…

Machine Learning · Computer Science 2023-01-02 Thomas Laurent , James H. von Brecht , Xavier Bresson

Large Language Models (LLMs) are transforming programming practices, offering significant capabilities for code generation activities. While researchers have explored the potential of LLMs in various domains, this paper focuses on their use…

Software Engineering · Computer Science 2026-05-04 Deborah Etsenake , Meiyappan Nagappan

Distribution shift has been a longstanding challenge for the reliable deployment of deep learning (DL) models due to unexpected accuracy degradation. Although DL has been becoming a driving force for large-scale source code analysis in the…

Software Engineering · Computer Science 2023-02-07 Qiang Hu , Yuejun Guo , Xiaofei Xie , Maxime Cordy , Lei Ma , Mike Papadakis , Yves Le Traon

Multimodal large language models (MLLMs) struggle with numerical regression under long-tailed target distributions. Token-level supervised fine-tuning (SFT) and point-wise regression rewards bias learning toward high-density regions,…

Computation and Language · Computer Science 2026-05-12 Yao Du , Shanshan Song , Xiaomeng Li

This paper studies the long-tailed semi-supervised learning (LTSSL) with distribution mismatch, where the class distribution of the labeled training data follows a long-tailed distribution and mismatches with that of the unlabeled training…

Machine Learning · Computer Science 2025-08-12 Yaxin Hou , Yuheng Jia

Large Language Models (LLMs) are rapidly becoming ubiquitous both as stand-alone tools and as components of current and future software systems. To enable usage of LLMs in the high-stake or safety-critical systems of 2030, they need to…

Software Engineering · Computer Science 2024-06-13 Sinclair Hudson , Sophia Jit , Boyue Caroline Hu , Marsha Chechik

We analyze neural scaling laws in a solvable model of last-layer fine-tuning where targets have intrinsic, instance-heterogeneous difficulty. In our Latent Instance Difficulty (LID) model, each input's target variance is governed by a…

Machine Learning · Computer Science 2026-01-08 Noam Levi

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

The widespread availability of large language models (LLMs) has changed how students engage with coding and problem-solving. While these tools may increase student productivity, they also make it more difficult for instructors to assess…

Software Engineering · Computer Science 2026-01-23 Yufan Zhang , Jaromir Savelka , Seth Copen Goldstein , Michael Conway

Semantic segmentation usually suffers from a long-tail data distribution. Due to the imbalanced number of samples across categories, the features of those tail classes may get squeezed into a narrow area in the feature space. Towards a…

Computer Vision and Pattern Recognition · Computer Science 2023-06-06 Yuchao Wang , Jingjing Fei , Haochen Wang , Wei Li , Tianpeng Bao , Liwei Wu , Rui Zhao , Yujun Shen

Recently, long-tailed image classification harvests lots of research attention, since the data distribution is long-tailed in many real-world situations. Piles of algorithms are devised to address the data imbalance problem by biasing the…

Computer Vision and Pattern Recognition · Computer Science 2023-02-06 Chaowei Fang , Dingwen Zhang , Wen Zheng , Xue Li , Le Yang , Lechao Cheng , Junwei Han

Background: Large Language Models emerged with the potential of provoking a revolution in software development (e.g., automating processes, workforce transformation). Although studies have started to investigate the perceived impact of LLMs…

Software Engineering · Computer Science 2026-05-22 Samuel Ferino , Rashina Hoda , John Grundy , Christoph Treude

A fundamental characteristic of natural language is the high rate at which speakers produce novel expressions. Because of this novelty, a heavy-tail of rare events accounts for a significant amount of the total probability mass of…

Computation and Language · Computer Science 2022-03-25 Benjamin LeBrun , Alessandro Sordoni , Timothy J. O'Donnell

Large Language Models (LLMs) have become instrumental in advancing software engineering (SE) tasks, showcasing their efficacy in code understanding and beyond. Like traditional SE tools, open-source collaboration is key in realising the…

Software Engineering · Computer Science 2024-04-10 Zhihao Lin , Wei Ma , Tao Lin , Yaowen Zheng , Jingquan Ge , Jun Wang , Jacques Klein , Tegawende Bissyande , Yang Liu , Li Li

The capability of large language models (LLMs) to generate, debug, and explain code has sparked the interest of researchers and educators in undergraduate programming, with many anticipating their transformative potential in programming…

Human-Computer Interaction · Computer Science 2024-06-11 Aadarsh Padiyath , Xinying Hou , Amy Pang , Diego Viramontes Vargas , Xingjian Gu , Tamara Nelson-Fromm , Zihan Wu , Mark Guzdial , Barbara Ericson