English
Related papers

Related papers: Quantile Regression for Distributional Reward Mode…

200 papers

Faithfulness, expressiveness, and elegance is the constant pursuit in machine translation. However, traditional metrics like \textit{BLEU} do not strictly align with human preference of translation quality. In this paper, we explore…

Computation and Language · Computer Science 2024-02-28 Nuo Xu , Jun Zhao , Can Zu , Sixian Li , Lu Chen , Zhihao Zhang , Rui Zheng , Shihan Dou , Wenjuan Qin , Tao Gui , Qi Zhang , Xuanjing Huang

Reinforcement learning (RL) often struggles with reward misalignment, where agents optimize given rewards but fail to exhibit the desired behaviors. This arises when the reward function incentivizes proxy behaviors misaligned with the true…

Machine Learning · Computer Science 2025-09-19 Mohammad Saif Nazir , Chayan Banerjee

While Reinforcement Learning from Human Feedback (RLHF) effectively aligns pretrained Large Language and Vision-Language Models (LLMs, and VLMs) with human preferences, its computational cost and complexity hamper its wider adoption. To…

Aligning large language models with pointwise absolute rewards has so far required online, on-policy algorithms such as PPO and GRPO. In contrast, simpler methods that can leverage offline or off-policy data, such as DPO and REBEL, are…

Machine Learning · Computer Science 2025-12-02 Simon Matrenok , Skander Moalla , Caglar Gulcehre

Reinforcement Learning from Human Feedback (RLHF) has shown potential in qualitative tasks where easily defined performance measures are lacking. However, there are drawbacks when RLHF is commonly used to optimize for average human…

Artificial Intelligence · Computer Science 2024-06-05 Li Ding , Jenny Zhang , Jeff Clune , Lee Spector , Joel Lehman

Reinforcement Learning with Human Feedback (RLHF) has become crucial for aligning Large Language Models (LLMs) with human intent. However, existing offline RLHF approaches suffer from overoptimization, where language models degrade by…

Machine Learning · Computer Science 2026-04-20 Sharan Sahu , Martin T. Wells

Recent strides in large language models (LLMs) have yielded remarkable performance, leveraging reinforcement learning from human feedback (RLHF) to significantly enhance generation and alignment capabilities. However, RLHF encounters…

Computation and Language · Computer Science 2024-05-31 Kuo Liao , Shuang Li , Meng Zhao , Liqun Liu , Mengge Xue , Zhenyu Hu , Honglin Han , Chengguo Yin

Reinforcement Learning from Human Feedback aligns the outputs of Large Language Models with human values and preferences. Central to this process is the reward model (RM), which translates human feedback into training signals for optimising…

Artificial Intelligence · Computer Science 2025-09-23 Zeyu Huang , Zihan Qiu , Zili Wang , Edoardo M. Ponti , Ivan Titov

Reinforcement Learning from Human Feedback (RLHF) has become a pivotal paradigm in artificial intelligence to align large models with human preferences. In this paper, we propose a novel statistical framework to simultaneously conduct the…

Machine Learning · Statistics 2026-05-01 Nan Lu , Ethan Lee , Ethan X. Fang , Junwei Lu

Reward Models, essential for guiding Large Language Model optimization, are typically trained on fixed preference datasets, resulting in rigid alignment to single, implicit preference distributions. This prevents adaptation to diverse…

Computation and Language · Computer Science 2025-07-08 Zhuohao Yu , Jiali Zeng , Weizheng Gu , Yidong Wang , Jindong Wang , Fandong Meng , Jie Zhou , Yue Zhang , Shikun Zhang , Wei Ye

Despite the significant progress made by existing retrieval augmented language models (RALMs) in providing trustworthy responses and grounding in reliable sources, they often overlook effective alignment with human preferences. In the…

Computation and Language · Computer Science 2024-12-19 Zhuoran Jin , Hongbang Yuan , Tianyi Men , Pengfei Cao , Yubo Chen , Kang Liu , Jun Zhao

Preference-based Reinforcement Learning (PbRL) provides a way to learn high-performance policies in environments where the reward signal is hard to specify, avoiding heuristic and time-consuming reward design. However, PbRL can suffer from…

Machine Learning · Computer Science 2025-07-02 Chenyang Cao , Miguel Rogel-García , Mohamed Nabail , Xueqian Wang , Nicholas Rhinehart

Reward models in RLHF are trained to score only the final token of a response - a choice that discards rich signal from every intermediate position and produces models whose token-level outputs are noise. We argue this is a missed…

Machine Learning · Computer Science 2026-04-28 Alex Nikulkov

Reinforcement learning from human feedback (RLHF) has been crucial in aligning large language models (LLMs) with human values. Traditionally, RLHF involves generating responses to a query and using a reward model to assign a reward to the…

Computation and Language · Computer Science 2024-12-04 Wenxuan Zhou , Shujian Zhang , Lingxiao Zhao , Tao Meng

Reward models (RMs) play a pivotal role in aligning large language models (LLMs) with human preferences. However, traditional RM training, which relies on response pairs tied to specific prompts, struggles to disentangle prompt-driven…

Reward models (RMs) play a critical role in aligning large language models (LLMs) with human preferences. Yet in the domain of tool learning, the lack of RMs specifically designed for function-calling tasks has limited progress toward more…

Artificial Intelligence · Computer Science 2026-01-14 Renhao Li , Jianhong Tu , Yang Su , Yantao Liu , Fei Huang , Hamid Alinejad-Rokny , Derek F. Wong , Junyang Lin , Min Yang

Reinforcement Learning with Human Feedback (RLHF) and Reinforcement Learning with Verifiable Rewards (RLVR) are the main RL paradigms used in LLM post-training, each offering distinct advantages. However, RLHF struggles with…

Computation and Language · Computer Science 2026-05-19 Zhilin Wang , Jiaqi Zeng , Olivier Delalleau , Ellie Evans , Daniel Egert , Hoo-Chang Shin , Felipe Soares , Yi Dong , Oleksii Kuchaiev

Reinforcement learning with human feedback for aligning large language models (LLMs) trains a reward model typically using ranking loss with comparison pairs.However, the training procedure suffers from an inherent problem: the uncontrolled…

Computation and Language · Computer Science 2024-09-19 Hang Zhou , Chenglong Wang , Yimin Hu , Tong Xiao , Chunliang Zhang , Jingbo Zhu

In aligning large language models (LLMs), reward models have played an important role, but are standardly trained as discriminative models and rely only on labeled human preference data. In this paper, we explore methods that train reward…

Computation and Language · Computer Science 2026-01-27 Chenglong Wang , Yang Gan , Yifu Huo , Yongyu Mu , Qiaozhi He , Murun Yang , Bei Li , Tong Xiao , Chunliang Zhang , Tongran Liu , Jingbo Zhu

Aligning human preference and value is an important requirement for contemporary foundation models. State-of-the-art techniques such as Reinforcement Learning from Human Feedback (RLHF) often consist of two stages: 1) supervised fine-tuning…

Artificial Intelligence · Computer Science 2024-10-29 Jiaxiang Li , Siliang Zeng , Hoi-To Wai , Chenliang Li , Alfredo Garcia , Mingyi Hong