English
Related papers

Related papers: DualReward: A Dynamic Reinforcement Learning Frame…

200 papers

Generating coherent and cohesive long-form texts is a challenging task. Previous works relied on large amounts of human-generated texts to train neural language models. However, few attempted to explicitly improve neural language models…

Computation and Language · Computer Science 2019-05-30 Woon Sang Cho , Pengchuan Zhang , Yizhe Zhang , Xiujun Li , Michel Galley , Chris Brockett , Mengdi Wang , Jianfeng Gao

Generative Flow Networks (GFlowNets) are powerful samplers for compositional objects that, by design, sample proportionally to a given non-negative reward. Nonetheless, in practice, they often struggle to explore the reward landscape…

Machine Learning · Computer Science 2026-03-17 Pedro Dall'Antonia , Tiago da Silva , Daniel Augusto de Souza , César Lincoln C. Mattos , Diego Mesquita

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

Recent advancements in flow-matching have enabled high-quality text-to-image generation. However, the deterministic nature of flow-matching models makes them poorly suited for reinforcement learning, a key tool for improving image quality…

Computer Vision and Pattern Recognition · Computer Science 2025-10-06 Benjamin Yu , Jackie Liu , Justin Cui

Recent advances in flow matching models have significantly improved text-to-image generation quality, but also introduce growing safety risks due to the generation of harmful or undesirable content. Existing concept erasure methods are…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Yi Sun , Zhiqi Zhang , Xinhao Zhong , Yimin Zhou , Shuoyang Sun , Bin Chen , Shu-Tao Xia , Ke Xu

When evaluating a learner's knowledge proficiency, the multiple-choice question is an efficient and widely used format in standardized tests. Nevertheless, generating these questions, particularly plausible distractors (incorrect options),…

Computation and Language · Computer Science 2024-05-30 Runfeng Lin , Dacheng Xu , Huijiang Wang , Zebiao Chen , Yating Wang , Shouqiang Liu

Designing reward functions for efficiently guiding reinforcement learning (RL) agents toward specific behaviors is a complex task. This is challenging since it requires the identification of reward structures that are not sparse and that…

Machine Learning · Computer Science 2023-11-01 Dhawal Gupta , Yash Chandak , Scott M. Jordan , Philip S. Thomas , Bruno Castro da Silva

While Large Language Models (LLMs) can generate fluent text, producing high-quality creative stories remains challenging. Reinforcement Learning (RL) offers a promising solution but faces two critical obstacles: designing reliable reward…

Artificial Intelligence · Computer Science 2026-01-13 Zhaoyan Li , Hang Lei , Yujia Wang , Lanbo Liu , Hao Liu , Liang Yu

We propose a novel reinforcement learning framework for post training large language models that does not rely on human in the loop feedback. Instead, our approach uses cross attention signals within the model itself to derive a self…

Artificial Intelligence · Computer Science 2025-04-18 Andrew Kiruluta , Andreas Lemos , Priscilla Burity

Designing reward functions is a longstanding challenge in reinforcement learning (RL); it requires specialized knowledge or domain data, leading to high costs for development. To address this, we introduce Text2Reward, a data-free framework…

Machine Learning · Computer Science 2024-05-28 Tianbao Xie , Siheng Zhao , Chen Henry Wu , Yitao Liu , Qian Luo , Victor Zhong , Yanchao Yang , Tao Yu

Reward models (RMs) are critical for aligning Large Language Models via Reinforcement Learning from Human Feedback (RLHF). While Generative Reward Models (GRMs) achieve superior accuracy through chain-of-thought (CoT) reasoning, they incur…

Computation and Language · Computer Science 2026-03-24 Jiayun Wu , Peixu Hou , Shan Qu , Peng Zhang , Ning Gu , Tun Lu

With the growing use of Retrieval-Augmented Generation (RAG), training large language models (LLMs) for context-sensitive reasoning and faithfulness is increasingly important. Existing RAG-oriented reinforcement learning (RL) methods rely…

Computation and Language · Computer Science 2026-03-06 Zhehao Tan , Yihan Jiao , Dan Yang , Junjie Wang , Duolin Sun , Jie Feng , Xidong Wang , Lei Liu , Yue Shen , Jian Wang , Jinjie Gu

In this paper, we investigate the following two limitations for the existing distractor generation (DG) methods. First, the quality of the existing DG methods are still far from practical use. There is still room for DG quality improvement.…

Computation and Language · Computer Science 2020-10-13 Ho-Lam Chung , Ying-Hong Chan , Yao-Chung Fan

Evaluating generative models with open-ended generation is challenging due to inconsistencies in response formats. Multiple-choice (MC) evaluation mitigates this issue, but generating high-quality distractors is time-consuming and…

Computation and Language · Computer Science 2025-06-16 Grace Byun , Jinho D. Choi

Reinforcement learning (RL) has shown its strength in challenging sequential decision-making problems. The reward function in RL is crucial to the learning performance, as it serves as a measure of the task completion degree. In real-world…

Machine Learning · Computer Science 2024-02-13 Siyuan Li , Shijie Han , Yingnan Zhao , By Liang , Peng Liu

As its availability and generality in online services, implicit feedback is more commonly used in recommender systems. However, implicit feedback usually presents noisy samples in real-world recommendation scenarios (such as misclicks or…

Information Retrieval · Computer Science 2024-05-29 Zhuangzhuang He , Yifan Wang , Yonghui Yang , Peijie Sun , Le Wu , Haoyue Bai , Jinqi Gong , Richang Hong , Min Zhang

Fine-tuning foundation models has emerged as a powerful approach for generating objects with specific desired properties. Reinforcement learning (RL) provides an effective framework for this purpose, enabling models to generate outputs that…

Machine Learning · Computer Science 2025-11-04 Pouya M. Ghari , Simone Sciabola , Ye Wang

Training chatbots using the reinforcement learning paradigm is challenging due to high-dimensional states, infinite action spaces and the difficulty in specifying the reward function. We address such problems using clustered actions instead…

Artificial Intelligence · Computer Science 2019-08-28 Heriberto Cuayáhuitl , Donghyeon Lee , Seonghan Ryu , Sungja Choi , Inchul Hwang , Jihie Kim

Reinforcement learning (RL) has recently become the dominant paradigm for strengthening the reasoning abilities of large language models (LLMs). Yet the rule-based reward functions commonly used on mathematical or programming benchmarks…

Artificial Intelligence · Computer Science 2025-09-09 Haoyang He , Zihua Rong , Kun Ji , Chenyang Li , Qing Huang , Chong Xia , Lan Yang , Honggang Zhang

Reinforcement learning (RL) with sparse and deceptive rewards is challenging because non-zero rewards are rarely obtained. Hence, the gradient calculated by the agent can be stochastic and without valid information. Recent studies that…

Machine Learning · Computer Science 2024-02-08 Guojian Wang , Faguo Wu , Xiao Zhang , Jianxiang Liu