English
Related papers

Related papers: RESTRAIN: From Spurious Votes to Signals -- Self-D…

200 papers

Reinforcement learning agents learn by encouraging behaviours which maximize their total reward, usually provided by the environment. In many environments, however, the reward is provided after a series of actions rather than each single…

Artificial Intelligence · Computer Science 2022-01-04 Mohammad Reza Bonyadi , Rui Wang , Maryam Ziaei

Natural Language Inference (NLI) or Recognizing Textual Entailment (RTE) aims at predicting the relation between a pair of sentences (premise and hypothesis) as entailment, contradiction or semantic independence. Although deep learning…

Computation and Language · Computer Science 2022-11-08 Mobashir Sadat , Cornelia Caragea

Semi-supervised learning (SSL) has witnessed great progress with various improvements in the self-training framework with pseudo labeling. The main challenge is how to distinguish high-quality pseudo labels against the confirmation bias.…

Machine Learning · Computer Science 2024-02-21 Siyuan Li , Weiyang Jin , Zedong Wang , Fang Wu , Zicheng Liu , Cheng Tan , Stan Z. Li

Large Language Models (LLMs) often produce plausible but poorly-calibrated answers, limiting their reliability on reasoning-intensive tasks. We present Reinforcement Learning from Self-Feedback (RLSF), a post-training stage that uses the…

Computation and Language · Computer Science 2025-07-30 Carel van Niekerk , Renato Vukovic , Benjamin Matthias Ruppik , Hsien-chin Lin , Milica Gašić

Medical Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities across diverse healthcare tasks. However, current post-training strategies, such as supervised fine-tuning and reinforcement learning, heavily depend…

Computer Vision and Pattern Recognition · Computer Science 2026-03-10 Dunyuan Xu , Xikai Yang , Juzheng Miao , Yaoqian Li , Jinpeng Li , Pheng-Ann Heng

In reinforcement learning (RL), value-based algorithms learn to associate each observation with the states and rewards that are likely to be reached from it. We observe that many self-supervised image pre-training methods bear similarity to…

Machine Learning · Computer Science 2025-06-16 Dibya Ghosh , Sergey Levine

Despite the large progress in supervised learning with neural networks, there are significant challenges in obtaining high-quality, large-scale and accurately labelled datasets. In such a context, how to learn in the presence of noisy…

Computer Vision and Pattern Recognition · Computer Science 2024-09-09 Chen Feng , Georgios Tzimiropoulos , Ioannis Patras

Training deep neural networks (DNNs) with limited supervision has been a popular research topic as it can significantly alleviate the annotation burden. Self-training has been successfully applied in semi-supervised learning tasks, but one…

Machine Learning · Computer Science 2023-02-17 Ran Xu , Yue Yu , Hejie Cui , Xuan Kan , Yanqiao Zhu , Joyce Ho , Chao Zhang , Carl Yang

Reinforcement learning from verifiable rewards (RLVR) has shown strong promise for LLM reasoning, but outcome-based RLVR remains inefficient on hard problems because correct final-answer rollouts are rare and sample-level credit assignment…

Machine Learning · Computer Science 2026-05-22 Xitai Jiang , Zihan Tang , Wenze Lin , Yang Yue , Shenzhi Wang , Gao Huang

Text style transfer is an important task in controllable language generation. Supervised approaches have pushed performance improvement on style-oriented rewriting such as formality conversion. However, challenges remain due to the scarcity…

Computation and Language · Computer Science 2022-05-20 Zhengyuan Liu , Nancy F. Chen

Reinforcement learning (RL) has significantly improved the reasoning ability of large language models. However, current reward models underperform in challenging reasoning scenarios and predominant RL training paradigms rely on rule-based…

Computation and Language · Computer Science 2025-07-30 Meng Zhou , Bei Li , Jiahao Liu , Xiaowen Shi , Yang Bai , Rongxiang Weng , Jingang Wang , Xunliang Cai

We investigate reinforcement learning (RL) for privileged planning in autonomous driving. State-of-the-art approaches for this task are rule-based, but these methods do not scale to the long tail. RL, on the other hand, is scalable and does…

Machine Learning · Computer Science 2025-08-22 Bernhard Jaeger , Daniel Dauner , Jens Beißwenger , Simon Gerstenecker , Kashyap Chitta , Andreas Geiger

Reinforcement learning with verifiable rewards (RLVR) has demonstrated superior performance in enhancing the reasoning capability of large language models (LLMs). However, this accuracy-oriented learning paradigm often suffers from entropy…

Artificial Intelligence · Computer Science 2026-01-19 Hongye Cao , Zhixin Bai , Ziyue Peng , Boyan Wang , Tianpei Yang , Jing Huo , Yuyao Zhang , Yang Gao

Training deep neural networks (DNNs) under weak supervision has attracted increasing research attention as it can significantly reduce the annotation cost. However, labels from weak supervision can be noisy, and the high capacity of DNNs…

Computation and Language · Computer Science 2023-05-02 Dawei Zhu , Xiaoyu Shen , Michael A. Hedderich , Dietrich Klakow

Self-improvement training enables the large reasoning models (LRMs) to improve themselves by self-generating reasoning trajectories as training data without external supervision. However, we find that this method often falls short in…

Computation and Language · Computer Science 2026-05-26 Qihuang Zhong , Liang Ding , Juhua Liu , Bo Du , Leszek Rutkowski , Dacheng Tao

An impediment to using Large Language Models (LLMs) for reasoning output verification is that LLMs struggle to reliably identify errors in thinking traces, particularly in long outputs, domains requiring expert knowledge, and problems…

Computation and Language · Computer Science 2026-02-09 Kate Sanders , Nathaniel Weir , Sapana Chaudhary , Kaj Bostrom , Huzefa Rangwala

Test-time training (TTT) adapts model parameters on unlabeled test instances during inference time, which continuously extends capabilities beyond the reach of offline training. Despite initial gains, existing TTT methods for LRMs plateau…

Machine Learning · Computer Science 2026-04-22 Qingyang Zhang , Xinke Kong , Haitao Wu , Qinghua Hu , Minghao Wu , Baosong Yang , Yu Cheng , Yun Luo , Ganqu Cui , Changqing Zhang

Manually annotating instruction data for large language models is difficult, costly, and hard to scale. Meanwhile, current automatic annotation methods typically rely on distilling synthetic data from proprietary LLMs, which not only limits…

Computation and Language · Computer Science 2024-08-21 Shu Chen , Xinyan Guan , Yaojie Lu , Hongyu Lin , Xianpei Han , Le Sun

Noisy labels damage the performance of deep networks. For robust learning, a prominent two-stage pipeline alternates between eliminating possible incorrect labels and semi-supervised training. However, discarding part of noisy labels could…

Machine Learning · Computer Science 2023-01-09 Mingcai Chen , Hao Cheng , Yuntao Du , Ming Xu , Wenyu Jiang , Chongjun Wang

Large Reasoning Models (LRMs) have shown remarkable reasoning capabilities, yet they often suffer from overthinking, expending redundant computational steps on simple problems, or underthinking, failing to explore sufficient reasoning paths…

Artificial Intelligence · Computer Science 2026-04-03 Yulin Li , Tengyao Tu , Li Ding , Junjie Wang , Huiling Zhen , Yixin Chen , Yong Li , Zhuotao Tian