English
Related papers

Related papers: Can LLMs Learn to Reason Robustly under Noisy Supe…

200 papers

Automatic annotation of large-scale datasets can introduce noisy training data labels, which adversely affect the learning process of deep neural networks (DNNs). Consequently, Noisy Labels Learning (NLL) has become a critical research…

Computer Vision and Pattern Recognition · Computer Science 2024-10-08 Maria Marrium , Arif Mahmood , Mohammed Bennamoun

Fine-tuning Large Language Models (LLMs) typically relies on large quantities of high-quality annotated data, or questions with well-defined ground truth answers in the case of Reinforcement Learning with Verifiable Rewards (RLVR). While…

Artificial Intelligence · Computer Science 2026-04-21 Justin Bauer , Thomas Walshe , Derek Pham , Harit Vishwakarma , Armin Parchami , Frederic Sala , Paroma Varma

While Reinforcement Learning for Verifiable Rewards (RLVR) is powerful for training large reasoning models, its training dynamics harbor a critical challenge: RL overfitting, where models gain training rewards but lose generalization. Our…

Artificial Intelligence · Computer Science 2025-11-07 Zeng Zhiyuan , Jiashuo Liu , Zhangyue Yin , Ge Zhang , Wenhao Huang , Xipeng Qiu

Incorrect labels in training data occur when human annotators make mistakes or when the data is generated via weak or distant supervision. It has been shown that complex noise-handling techniques - by modeling, cleaning or filtering the…

Computation and Language · Computer Science 2022-04-21 Dawei Zhu , Michael A. Hedderich , Fangzhou Zhai , David Ifeoluwa Adelani , Dietrich Klakow

Label noise significantly degrades the generalization ability of deep models in applications. Effective strategies and approaches, \textit{e.g.} re-weighting, or loss correction, are designed to alleviate the negative impact of label noise…

Machine Learning · Computer Science 2021-11-09 Haoliang Sun , Chenhui Guo , Qi Wei , Zhongyi Han , Yilong Yin

Distant and weak supervision allow to obtain large amounts of labeled training data quickly and cheaply, but these automatic annotations tend to contain a high amount of errors. A popular technique to overcome the negative effects of these…

Machine Learning · Computer Science 2021-03-02 Michael A. Hedderich , Dawei Zhu , Dietrich Klakow

Reinforcement learning with verifiable rewards (RLVR) has become central to post-training reasoning models, yet a key limitation of existing studies is their narrow view of the reasoning space: difficulty is treated as reasoning depth…

Computation and Language · Computer Science 2026-05-27 Yihua Zhu , Qianying Liu , Fei Cheng , Jiaxin Wang , Akiko Aizawa , Sadao Kurohashi , Hidetoshi Shimodaira

Large reasoning models (LRMs) are typically trained using reinforcement learning with verifiable reward (RLVR) to enhance their reasoning abilities. In this paradigm, policies are updated using both positive and negative self-generated…

Computation and Language · Computer Science 2025-12-29 Xinyu Tang , Yuliang Zhan , Zhixun Li , Wayne Xin Zhao , Zhenduo Zhang , Zujie Wen , Zhiqiang Zhang , Jun Zhou

Most reinforcement learning (RL) methods for training large language models (LLMs) require ground-truth labels or task-specific verifiers, limiting scalability when correctness is ambiguous or expensive to obtain. We introduce Reinforcement…

Neural and Evolutionary Computing · Computer Science 2026-01-30 Micah Rentschler , Jesse Roberts

Reinforcement Learning with Verifiable Rewards (RLVR) is a powerful framework for improving the reasoning abilities of Large Language Models (LLMs). However, current methods such as GRPO rely only on problems where the model responses to…

Computation and Language · Computer Science 2026-02-10 Thanh-Long V. Le , Myeongho Jeon , Kim Vu , Viet Lai , Eunho Yang

Labeling errors in datasets are common, arising in a variety of contexts, such as human labeling, noisy labeling, and weak labeling (i.e., image classification). Although neural networks (NNs) can tolerate modest amounts of these errors,…

Machine Learning · Computer Science 2025-02-18 Louis L. Chen , Bobbie Chern , Eric Eckstrand , Amogh Mahapatra , Johannes O. Royset

Deep learning has made many remarkable achievements in many fields but suffers from noisy labels in datasets. The state-of-the-art learning with noisy label method Co-teaching and Co-teaching+ confronts the noisy label by mutual-information…

Computer Vision and Pattern Recognition · Computer Science 2022-08-16 Jiarun Liu , Daguang Jiang , Yukun Yang , Ruirui Li

Label-noise learning (LNL) aims to increase the model's generalization given training data with noisy labels. To facilitate practical LNL algorithms, researchers have proposed different label noise types, ranging from class-conditional to…

Machine Learning · Computer Science 2024-02-13 Jingfeng Zhang , Bo Song , Haohan Wang , Bo Han , Tongliang Liu , Lei Liu , Masashi Sugiyama

Learning in the presence of label noise is a challenging yet important task: it is crucial to design models that are robust in the presence of mislabeled datasets. In this paper, we discover that a new class of loss functions called the…

Machine Learning · Computer Science 2020-02-18 Liu Ziyin , Blair Chen , Ru Wang , Paul Pu Liang , Ruslan Salakhutdinov , Louis-Philippe Morency , Masahito Ueda

Reinforcement learning with verifiable rewards (RLVR) has emerged as a powerful paradigm for enhancing the reasoning capabilities of large language models (LLMs). Unlike traditional RL approaches, RLVR leverages rule-based feedback to guide…

Computation and Language · Computer Science 2025-08-19 Jia Deng , Jie Chen , Zhipeng Chen , Daixuan Cheng , Fei Bai , Beichen Zhang , Yinqian Min , Yanzipeng Gao , Wayne Xin Zhao , Ji-Rong Wen

The real-world data is often susceptible to label noise, which might constrict the effectiveness of the existing state of the art algorithms for ordinal regression. Existing works on ordinal regression do not take label noise into account.…

Machine Learning · Computer Science 2020-01-28 Bhanu Garg , Naresh Manwani

Label distribution learning (LDL) trains a model to predict the relevance of a set of labels (called label distribution (LD)) to an instance. The previous LDL methods all assumed the LDs of the training instances are accurate. However,…

Machine Learning · Computer Science 2023-08-29 Zhiqiang Kou , Yuheng Jia , Jing Wang , Xin Geng

The prevailing paradigm for training large reasoning models--combining Supervised Fine-Tuning (SFT) with Reinforcement Learning with Verifiable Rewards (RLVR)--is fundamentally constrained by its reliance on high-quality, human-annotated…

Machine Learning · Computer Science 2026-03-24 Yuanfu Wang , Zhixuan Liu , Xiangtian Li , Chaochao Lu , Chao Yang

Reinforcement learning with verifiable rewards (RLVR) has demonstrated significant success in enhancing mathematical reasoning and coding performance of large language models (LLMs), especially when structured reference answers are…

Computation and Language · Computer Science 2025-04-02 Yi Su , Dian Yu , Linfeng Song , Juntao Li , Haitao Mi , Zhaopeng Tu , Min Zhang , Dong Yu

Label noise is a critical factor that degrades the generalization performance of deep neural networks, thus leading to severe issues in real-world problems. Existing studies have employed strategies based on either loss or uncertainty to…

Machine Learning · Computer Science 2020-08-17 Wonyoung Shin , Jung-Woo Ha , Shengzhe Li , Yongwoo Cho , Hoyean Song , Sunyoung Kwon