English
Related papers

Related papers: The Past Mistake is the Future Wisdom: Error-drive…

200 papers

Language models (LMs) are trained on billions of tokens in an attempt to recover the true language distribution. Still, vanilla random sampling from LMs yields low quality generations. Decoding algorithms attempt to restrict the LM…

Machine Learning · Computer Science 2026-01-06 Kareem Ahmed , Sameer Singh

Solving math word problems is the task that analyses the relation of quantities and requires an accurate understanding of contextual natural language information. Recent studies show that current models rely on shallow heuristics to predict…

Computation and Language · Computer Science 2022-11-30 Yibin Shen , Qianying Liu , Zhuoyuan Mao , Fei Cheng , Sadao Kurohashi

Reinforcement learning (RL) has become a central component of post-training for large language models (LLMs), particularly for complex reasoning tasks that require stable optimization over long generation horizons. However, achieving…

Machine Learning · Computer Science 2026-02-17 Yuepeng Sheng , Yuwei Huang , Shuman Liu , Anxiang Zeng , Haibo Zhang

The dichotomy between the challenging nature of obtaining annotations for activities, and the more straightforward nature of data collection from wearables, has resulted in significant interest in the development of techniques that utilize…

Machine Learning · Computer Science 2022-11-14 Harish Haresamudram , Irfan Essa , Thomas Ploetz

Aligning large-scale vision-language models (VLMs) for complex reasoning via reinforcement learning is often hampered by the limitations of existing policy optimization algorithms, such as static training schedules and the rigid, uniform…

Artificial Intelligence · Computer Science 2025-10-02 Yunhao Wang , Ziting Li , Shuai Chen , Tao Liu , Chao Song , Junjie Jiang , Jian Zhu , Peng Gao , Bin Qin

We previously proposed contextual spelling correction (CSC) to correct the output of end-to-end (E2E) automatic speech recognition (ASR) models with contextual information such as name, place, etc. Although CSC has achieved reasonable…

Sound · Computer Science 2023-02-23 Xiaoqiang Wang , Yanqing Liu , Jinyu Li , Sheng Zhao

Error correction (EC) based on large language models is an emerging technology to enhance the performance of automatic speech recognition (ASR) systems. Generally, training data for EC are collected by automatically pairing a large set of…

Computation and Language · Computer Science 2024-10-17 Takuma Udagawa , Masayuki Suzuki , Masayasu Muraoka , Gakuto Kurata

Chinese input methods are used to convert pinyin sequence or other Latin encoding systems into Chinese character sentences. For more effective pinyin-to-character conversion, typical Input Method Engines (IMEs) rely on a predefined…

Computation and Language · Computer Science 2017-12-13 Xihu Zhang , Chu Wei , Hai Zhao

Continual learning aims to learn multiple tasks sequentially while preserving prior knowledge, but faces the challenge of catastrophic forgetting when adapting to new tasks. Recently, approaches leveraging pre-trained models have gained…

Computer Vision and Pattern Recognition · Computer Science 2025-11-12 Quan Cheng , Yuanyu Wan , Lingyu Wu , Chenping Hou , Lijun Zhang

Proximal Policy Optimization (PPO) is central to aligning Large Language Models (LLMs) in reasoning tasks with verifiable rewards. However, standard token-level PPO struggles in this setting due to the instability of temporal credit…

Artificial Intelligence · Computer Science 2026-04-13 Tianyi Wang , Yixia Li , Long Li , Yibiao Chen , Shaohan Huang , Yun Chen , Peng Li , Yang Liu , Guanhua Chen

Given multiple non-convex objective functions and objective-specific weights, Chebyshev scalarization (CS) is a well-known approach to obtain an Exact Pareto Optimal (EPO), i.e., a solution on the Pareto front (PF) that intersects the ray…

Machine Learning · Computer Science 2023-09-19 Debabrata Mahapatra , Vaibhav Rajan

Reinforcement learning has significantly enhanced the reasoning capabilities of Large Language Models (LLMs) in complex problem-solving tasks. Recently, the introduction of DeepSeek R1 has inspired a surge of interest in leveraging…

Machine Learning · Computer Science 2025-08-07 Jinghang Han , Jiawei Chen , Hang Shao , Hao Ma , Mingcheng Li , Xintian Shen , Lihao Zheng , Wei Chen , Tao Wei , Lihua Zhang

Chinese text recognition is more challenging than Latin text due to the large amount of fine-grained Chinese characters and the great imbalance over classes, which causes a serious overfitting problem. We propose to apply Maximum Entropy…

Computer Vision and Pattern Recognition · Computer Science 2020-07-10 Changxu Cheng , Wuheng Xu , Xiang Bai , Bin Feng , Wenyu Liu

Large language models (LLMs) often make accurate next token predictions but their confidence in these predictions can be poorly calibrated: high-confidence predictions are frequently wrong, and low-confidence predictions may be correct.…

Machine Learning · Computer Science 2026-02-03 Nisarg Parikh , Ananya Sai , Pannaga Shivaswamy , Kunjal Panchal , Andrew Lan

Accurate mathematical reasoning with Large Language Models (LLMs) is crucial in revolutionizing domains that heavily rely on such reasoning. However, LLMs often encounter difficulties in certain aspects of mathematical reasoning, leading to…

Artificial Intelligence · Computer Science 2025-02-11 Kuofeng Gao , Huanqia Cai , Qingyao Shuai , Dihong Gong , Zhifeng Li

Simultaneous translation has many important application scenarios and attracts much attention from both academia and industry recently. Most existing frameworks, however, have difficulties in balancing between the translation quality and…

Computation and Language · Computer Science 2020-05-05 Renjie Zheng , Mingbo Ma , Baigong Zheng , Kaibo Liu , Liang Huang

This report describes a pre-trained language model Erlangshen with propensity-corrected loss, the No.1 in CLUE Semantic Matching Challenge. In the pre-training stage, we construct a dynamic masking strategy based on knowledge in Masked…

Computation and Language · Computer Science 2022-08-08 Junjie Wang , Yuxiang Zhang , Ping Yang , Ruyi Gan

Reinforcement learning (RL) has become a cornerstone for fine-tuning Large Language Models (LLMs), with Proximal Policy Optimization (PPO) serving as the de facto standard algorithm. Despite its ubiquity, we argue that the core ratio…

Machine Learning · Computer Science 2026-05-27 Penghui Qi , Xiangxin Zhou , Zichen Liu , Tianyu Pang , Chao Du , Min Lin , Wee Sun Lee

Large Language Models (LLMs) often exhibit implicit biases and discriminatory tendencies that reflect underlying social stereotypes. While recent alignment techniques such as RLHF and DPO have mitigated some of these issues, they remain…

Computation and Language · Computer Science 2025-11-11 Deng Yixuan , Ji Xiaoqiang

Real-world decision-making problems are often marked by complex, uncertain dynamics that can shift or break under changing conditions. Traditional Model-Based Reinforcement Learning (MBRL) approaches learn predictive models of environment…

Machine Learning · Computer Science 2025-03-14 Alberto Caron , Vasilios Mavroudis , Chris Hicks