English
Related papers

Related papers: Rethinking Exposure Bias In Language Modeling

200 papers

Reinforcement learning (RL) has been widely used in text generation to alleviate the exposure bias issue or to utilize non-parallel datasets. The reward function plays an important role in making RL training successful. However, previous…

Machine Learning · Computer Science 2023-01-19 Yongchang Hao , Yuxin Liu , Lili Mou

Pre-trained language models (PLMs) are trained on data that inherently contains gender biases, leading to undesirable impacts. Traditional debiasing methods often rely on external corpora, which may lack quality, diversity, or demographic…

Computation and Language · Computer Science 2025-03-13 Liu Yu , Ludie Guo , Ping Kuang , Fan Zhou

Reinforcement learning has become the central approach for language models (LMs) to learn from environmental reward or feedback. In practice, the environmental feedback is usually sparse and delayed. Learning from such signals is…

Machine Learning · Computer Science 2026-02-17 Taiwei Shi , Sihao Chen , Bowen Jiang , Linxin Song , Longqi Yang , Jieyu Zhao

A popular strategy to train recurrent neural networks (RNNs), known as ``teacher forcing'' takes the ground truth as input at each time step and makes the later predictions partly conditioned on those inputs. Such training strategy impairs…

Computation and Language · Computer Science 2021-03-23 Liping Yuan , Jiangtao Feng , Xiaoqing Zheng , Xuanjing Huang

Biases in the dataset often enable the model to achieve high performance on in-distribution data, while poorly performing on out-of-distribution data. To mitigate the detrimental effect of the bias on the networks, previous works have…

Computation and Language · Computer Science 2023-12-07 Eojin Jeon , Mingyu Lee , Juhyeong Park , Yeachan Kim , Wing-Lam Mok , SangKeun Lee

The performance of adversarial dialogue generation models relies on the quality of the reward signal produced by the discriminator. The reward signal from a poor discriminator can be very sparse and unstable, which may lead the generator to…

Computation and Language · Computer Science 2018-12-11 Ziming Li , Julia Kiseleva , Maarten de Rijke

Language models can learn a range of capabilities from unsupervised training on text corpora. However, to solve a particular problem (such as text summarization) it is typically necessary to fine-tune them on a task-specific dataset. It is…

Computation and Language · Computer Science 2022-03-16 Adam Gleave , Geoffrey Irving

The correct specification of reward models is a well-known challenge in reinforcement learning. Hand-crafted reward functions often lead to inefficient or suboptimal policies and may not be aligned with user values. Reinforcement learning…

Artificial Intelligence · Computer Science 2024-10-24 Muhan Lin , Shuyang Shi , Yue Guo , Behdad Chalaki , Vaishnav Tadiparthi , Ehsan Moradi Pari , Simon Stepputtis , Joseph Campbell , Katia Sycara

Reinforcement Learning (RL) has been witnessed its potential for training a dialogue policy agent towards maximizing the accumulated rewards given from users. However, the reward can be very sparse for it is usually only provided at the end…

Computation and Language · Computer Science 2021-11-03 Hongru Wang , Huimin Wang , Zezhong Wang , Kam-Fai Wong

Many natural language inference (NLI) datasets contain biases that allow models to perform well by only using a biased subset of the input, without considering the remainder features. For instance, models are able to make a classification…

Computation and Language · Computer Science 2021-09-01 Dimion Asael , Zachary Ziegler , Yonatan Belinkov

Fairness in classification tasks has traditionally focused on bias removal from neural representations, but recent trends favor algorithmic methods that embed fairness into the training process. These methods steer models towards fair…

Machine Learning · Computer Science 2024-07-16 Leon Eshuijs , Shihan Wang , Antske Fokkens

Reinforcement Learning (RL) methods have emerged as a popular choice for training an efficient and effective dialogue policy. However, these methods suffer from sparse and unstable reward signals returned by a user simulator only when a…

Artificial Intelligence · Computer Science 2020-09-18 Ziming Li , Sungjin Lee , Baolin Peng , Jinchao Li , Julia Kiseleva , Maarten de Rijke , Shahin Shayandeh , Jianfeng Gao

In Large Language Models, Retrieval-Augmented Generation (RAG) systems can significantly enhance the performance of large language models by integrating external knowledge. However, RAG also introduces new security risks. Existing research…

Machine Learning · Computer Science 2025-06-16 Linlin Wang , Tianqing Zhu , Laiqiao Qin , Longxiang Gao , Wanlei Zhou

Reinforcement learning with verifiable rewards (RLVR) scales the reasoning ability of large language models (LLMs) but remains bottlenecked by limited labeled samples for continued data scaling. Reinforcement learning with intrinsic rewards…

Machine Learning · Computer Science 2025-10-13 Chuyi Tan , Peiwen Yuan , Xinglin Wang , Yiwei Li , Shaoxiong Feng , Yueqi Zhang , Jiayi Shi , Ji Zhang , Boyuan Pan , Yao Hu , Kan Li

Large pre-trained language models have shown remarkable performance over the past few years. These models, however, sometimes learn superficial features from the dataset and cannot generalize to the distributions that are dissimilar to the…

Computation and Language · Computer Science 2022-10-31 Jieyu Zhao , Xuezhi Wang , Yao Qin , Jilin Chen , Kai-Wei Chang

Recent studies have shown that reinforcement learning (RL) models are vulnerable in various noisy scenarios. For instance, the observed reward channel is often subject to noise in practice (e.g., when rewards are collected through sensors),…

Machine Learning · Computer Science 2020-02-04 Jingkang Wang , Yang Liu , Bo Li

Large language models (LLMs) increasingly serve as reasoners and automated evaluators, yet they remain susceptible to cognitive biases -- often altering their reasoning when faced with spurious prompt-level cues such as consensus claims or…

Computers and Society · Computer Science 2026-04-07 Qian Wang , Xuandong Zhao , Zirui Zhang , Zhanzhi Lou , Nuo Chen , Dawn Song , Bingsheng He

Reinforcement learning (RL) is a promising approach for aligning large language models (LLMs) knowledge with sequential decision-making tasks. However, few studies have thoroughly investigated the impact on LLM agents capabilities of…

Active learning is a powerful tool when labelling data is expensive, but it introduces a bias because the training data no longer follows the population distribution. We formalize this bias and investigate the situations in which it can be…

Machine Learning · Statistics 2021-06-01 Sebastian Farquhar , Yarin Gal , Tom Rainforth

Denoising diffusion models have emerged as a dominant approach for image generation, however they still suffer from slow convergence in training and color shift issues in sampling. In this paper, we identify that these obstacles can be…

Computer Vision and Pattern Recognition · Computer Science 2024-08-06 Hu Yu , Li Shen , Jie Huang , Hongsheng Li , Feng Zhao