English
Related papers

Related papers: On the Robustness of Reward Models for Language Mo…

200 papers

Reinforcement learning from human feedback (RLHF) has emerged as a powerful technique to make large language models (LLMs) more capable in complex settings. RLHF proceeds as collecting human preference data, training a reward model on said…

Machine Learning · Computer Science 2024-02-05 Nathan Lambert , Roberto Calandra

Reward models (RM) capture the values and preferences of humans and play a central role in Reinforcement Learning with Human Feedback (RLHF) to align pretrained large language models (LLMs). Traditionally, training these models relies on…

Machine Learning · Computer Science 2024-09-12 Yifei He , Haoxiang Wang , Ziyan Jiang , Alexandros Papangelis , Han Zhao

Reinforcement Learning from Human Feedback (RLHF) has been crucial to the recent success of Large Language Models (LLMs), however, it is often a complex and brittle process. In the classical RLHF framework, a reward model is first trained…

Machine Learning · Computer Science 2024-11-06 Rafael Rafailov , Yaswanth Chittepu , Ryan Park , Harshit Sikchi , Joey Hejna , Bradley Knox , Chelsea Finn , Scott Niekum

Reinforcement learning based fine-tuning of large language models (LLMs) on human preferences has been shown to enhance both their capabilities and safety behavior. However, in cases related to safety, without precise instructions to human…

Artificial Intelligence · Computer Science 2024-11-05 Tong Mu , Alec Helyar , Johannes Heidecke , Joshua Achiam , Andrea Vallone , Ian Kivlichan , Molly Lin , Alex Beutel , John Schulman , Lilian Weng

The safety alignment of large language models (LLMs) often relies on reinforcement learning from human feedback (RLHF), which requires human annotations to construct preference datasets. Given the challenge of assigning overall quality…

Computation and Language · Computer Science 2025-11-12 Xiaomin Li , Xupeng Chen , Jingxuan Fan , Eric Hanchen Jiang , Mingye Gao

In reinforcement learning, specifying reward functions that capture the intended task can be very challenging. Reward learning aims to address this issue by learning the reward function. However, a learned reward model may have a low error…

Machine Learning · Computer Science 2025-07-09 Lukas Fluri , Leon Lang , Alessandro Abate , Patrick Forré , David Krueger , Joar Skalse

The reward model (RM) that represents human preferences plays a crucial role in optimizing the outputs of large language models (LLMs), e.g., through reinforcement learning from human feedback (RLHF) or rejection sampling. However, a long…

Artificial Intelligence · Computer Science 2025-04-22 Yizhou Chen , Yawen Liu , Xuesi Wang , Qingtao Yu , Guangda Huzhang , Anxiang Zeng , Han Yu , Zhiming Zhou

Reinforcement Learning with Verifiable Rewards (RLVR) has recently strengthened LLM reasoning, but its focus on final answer correctness leaves a critical gap: it does not ensure the robustness of the reasoning process itself. We adopt a…

Machine Learning · Computer Science 2026-02-10 Hyunseok Lee , Soheil Abbasloo , Jihoon Tack , Jinwoo Shin

After the pretraining stage of LLMs, techniques such as SFT, RLHF, RLVR, and RFT are applied to enhance instruction-following ability, mitigate undesired responses, improve reasoning capability and enable efficient domain adaptation with…

Computation and Language · Computer Science 2025-10-17 Zhichao Wang , Andy Wong , Ruslan Belkin

This work tackles the problem of overoptimization in reinforcement learning from human feedback (RLHF), a prevalent technique for aligning models with human preferences. RLHF relies on reward or preference models trained on \emph{fixed…

Machine Learning · Computer Science 2025-03-11 Dhawal Gupta , Adam Fisch , Christoph Dann , Alekh Agarwal

Reinforcement learning from human feedback (RLHF) has become a core post-training step for aligning large language models, yet the reward signal used in RLHF is only a learned proxy for true human utility. From an operations research…

Machine Learning · Computer Science 2026-05-19 Yikai Wang , Shang Liu , Jose Blanchet

Reinforcement Learning from Human Feedback (RLHF) is a widely adopted approach for aligning large language models with human values. However, RLHF relies on a reward model that is trained with a limited amount of human preference data,…

Machine Learning · Computer Science 2024-10-23 Shun Zhang , Zhenfang Chen , Sunli Chen , Yikang Shen , Zhiqing Sun , Chuang Gan

Current reinforcement learning from human feedback (RLHF) pipelines for large language model (LLM) alignment typically assign scalar rewards to sequences, using the final token as a surrogate indicator for the quality of the entire…

Machine Learning · Computer Science 2025-04-24 Ryan Koo , Ian Yang , Vipul Raheja , Mingyi Hong , Kwang-Sung Jun , Dongyeop Kang

During the preference optimization of large language models (LLMs), distribution shifts may arise between newly generated model samples and the data used to train the reward model (RM). This shift reduces the efficacy of the RM, which in…

Machine Learning · Computer Science 2025-06-11 Tianyuan Shi , Canbin Huang , Fanqi Wan , Longguang Zhong , Ziyi Yang , Weizhou Shen , Xiaojun Quan , Ming Yan

Reinforcement Learning from Human Feedback (RLHF) is a pivotal technique that aligns language models closely with human-centric values. The initial phase of RLHF involves learning human values using a reward model from ranking data. It is…

Machine Learning · Computer Science 2024-01-30 Banghua Zhu , Michael I. Jordan , Jiantao Jiao

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

In safety-critical domains, reinforcement learning (RL) agents must often satisfy strict, zero-cost safety constraints while accomplishing tasks. Existing model-free methods frequently either fail to achieve near-zero safety violations or…

Machine Learning · Computer Science 2026-05-11 Dominik Wagner , Ankit Kanwar , Luke Ong

Reward modeling is a key step in building safe foundation models when applying reinforcement learning from human feedback (RLHF) to align Large Language Models (LLMs). However, reward modeling based on the Bradley-Terry (BT) model assumes a…

Artificial Intelligence · Computer Science 2025-09-24 Jingyan Shen , Jiarui Yao , Rui Yang , Yifan Sun , Feng Luo , Rui Pan , Tong Zhang , Han Zhao

Reinforcement learning (RL) can align language models with non-differentiable reward signals, such as human preferences. However, a major challenge arises from the sparsity of these reward signals - typically, there is only a single reward…

Computation and Language · Computer Science 2024-02-20 Meng Cao , Lei Shu , Lei Yu , Yun Zhu , Nevan Wichers , Yinxiao Liu , Lei Meng

In Reinforcement Learning (RL), it is commonly assumed that an immediate reward signal is generated for each action taken by the agent, helping the agent maximize cumulative rewards to obtain the optimal policy. However, in many real-world…

Machine Learning · Computer Science 2024-10-29 Yuting Tang , Xin-Qiang Cai , Yao-Xiang Ding , Qiyu Wu , Guoqing Liu , Masashi Sugiyama
‹ Prev 1 4 5 6 7 8 10 Next ›