English
Related papers

Related papers: Debiasing Reward Models by Representation Learning…

200 papers

Language models serve as proxies for human preference judgements in alignment and evaluation, yet they exhibit systematic miscalibration, prioritizing superficial patterns over substantive qualities. This bias manifests as overreliance on…

Computation and Language · Computer Science 2026-03-05 Anirudh Bharadwaj , Chaitanya Malaviya , Nitish Joshi , Mark Yatskar

Preference alignment in Large Language Models (LLMs) has significantly improved their ability to adhere to human instructions and intentions. However, existing direct alignment algorithms primarily focus on relative preferences and often…

Machine Learning · Computer Science 2025-05-13 Shenao Zhang , Zhihan Liu , Boyi Liu , Yufeng Zhang , Yingxiang Yang , Yongfei Liu , Liyu Chen , Tao Sun , Zhaoran Wang

This paper investigates the integration of response time data into human preference learning frameworks for more effective reward model elicitation. While binary preference data has become fundamental in fine-tuning foundation models,…

Machine Learning · Computer Science 2025-10-29 Ayush Sawarni , Sahasrajit Sarmasarkar , Vasilis Syrgkanis

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 NLP, recent work has seen increased focus on spurious correlations between various features and labels in training data, and how these influence model behavior. However, the presence and effect of such correlations are typically examined…

Computation and Language · Computer Science 2023-06-06 Sofia Serrano , Jesse Dodge , Noah A. Smith

The emergence of reinforcement learning in post-training of large language models has sparked significant interest in reward models. Reward models assess the quality of sampled model outputs to generate training signals. This task is also…

Computation and Language · Computer Science 2025-10-06 Sebastian Gehrmann

Reinforcement learning from human feedback serves as a crucial bridge, aligning large language models with human and societal values. This alignment requires a vast corpus of human feedback to learn a reward model, which is subsequently…

Computation and Language · Computer Science 2023-11-30 Wei Shen , Rui Zheng , Wenyu Zhan , Jun Zhao , Shihan Dou , Tao Gui , Qi Zhang , Xuanjing Huang

Our goal is for agents to optimize the right reward function, despite how difficult it is for us to specify what that is. Inverse Reinforcement Learning (IRL) enables us to infer reward functions from demonstrations, but it usually assumes…

Machine Learning · Computer Science 2019-06-25 Rohin Shah , Noah Gundotra , Pieter Abbeel , Anca D. Dragan

One of the challenges of aligning large models with human preferences lies in both the data requirements and the technical complexities of current approaches. Predominant methods, such as RLHF, involve multiple steps, each demanding…

Machine Learning · Computer Science 2025-03-19 Siliang Zeng , Yao Liu , Huzefa Rangwala , George Karypis , Mingyi Hong , Rasool Fakoor

The complexity of designing reward functions has been a major obstacle to the wide application of deep reinforcement learning (RL) techniques. Describing an agent's desired behaviors and properties can be difficult, even for experts. A new…

Machine Learning · Computer Science 2024-05-09 Wanqi Xue , Bo An , Shuicheng Yan , Zhongwen Xu

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

AI agents are commonly aligned with "human values" through reinforcement learning from human feedback (RLHF), where a single reward model is learned from aggregated human feedback and used to align an agent's behavior. However, human values…

Artificial Intelligence · Computer Science 2025-06-24 Carter Blair , Kate Larson , Edith Law

The development of trustworthy conversational information-seeking systems relies on dialogue models that can generate faithful and accurate responses based on relevant knowledge texts. However, two main challenges hinder this task. Firstly,…

Computation and Language · Computer Science 2023-11-03 Wanyu Du , Yangfeng Ji

The success of reinforcement learning from human feedback (RLHF) in language model alignment is strongly dependent on the quality of the underlying reward model. In this paper, we present a novel approach to improve reward model quality by…

Computation and Language · Computer Science 2024-10-28 Alizée Pace , Jonathan Mallinson , Eric Malmi , Sebastian Krause , Aliaksei Severyn

Rewards play an essential role in reinforcement learning. In contrast to rule-based game environments with well-defined reward functions, complex real-world robotic applications, such as contact-rich manipulation, lack explicit and…

Machine Learning · Computer Science 2022-05-30 Yuning Wu , Jieliang Luo , Hui Li

Reinforcement Learning from Human Feedback relies on reward models to align large language models with human preferences. However, RLHF often suffers from reward hacking, wherein policy learning exploits flaws in the trained reward model to…

Machine Learning · Computer Science 2025-05-20 Kangwen Zhao , Jianfeng Cai , Jinhua Zhu , Ruopei Sun , Dongyun Xue , Wengang Zhou , Li Li , Houqiang Li

In reinforcement learning (RL), agents continually interact with the environment and use the feedback to refine their behavior. To guide policy optimization, reward models are introduced as proxies of the desired objectives, such that when…

Machine Learning · Computer Science 2025-06-19 Rui Yu , Shenghua Wan , Yucen Wang , Chen-Xiao Gao , Le Gan , Zongzhang Zhang , De-Chuan Zhan

Preference-based reward learning is widely used for shaping agent behavior to match a user's preference, yet its sparse binary feedback makes it especially vulnerable to causal confusion. The learned reward often latches onto spurious…

Artificial Intelligence · Computer Science 2026-03-06 Minjune Hwang , Yigit Korkmaz , Daniel Seita , Erdem Bıyık

Reward models are pivotal for aligning Large Language Models (LLMs) with human preferences. Existing approaches face two key limitations: Discriminative reward models require large-scale annotated data, as they cannot exploit the preference…

Computation and Language · Computer Science 2026-02-03 Yongfu Xue

Many machine learning algorithms are trained and evaluated by splitting data from a single source into training and test sets. While such focus on in-distribution learning scenarios has led to interesting advancement, it has not been able…

Computer Vision and Pattern Recognition · Computer Science 2020-07-02 Hyojin Bahng , Sanghyuk Chun , Sangdoo Yun , Jaegul Choo , Seong Joon Oh