English
Related papers

Related papers: Variance-aware Reward Modeling with Anchor Guidanc…

200 papers

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

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

Reinforcement Learning from Human Feedback has become the standard paradigm for language model alignment, where reward models directly determine alignment effectiveness. In this work, we focus on how to evaluate the generalizability of…

Computation and Language · Computer Science 2026-05-05 Yangyang Zhou , Yi-Chen Li

As more machine learning agents interact with humans, it is increasingly a prospect that an agent trained to perform a task optimally, using only a measure of task performance as feedback, can violate societal norms for acceptable behavior…

Machine Learning · Computer Science 2021-04-20 Md Sultan Al Nahian , Spencer Frazier , Brent Harrison , Mark Riedl

Object detection has been dominated by anchor-based detectors for several years. Recently, anchor-free detectors have become popular due to the proposal of FPN and Focal Loss. In this paper, we first point out that the essential difference…

Computer Vision and Pattern Recognition · Computer Science 2020-06-23 Shifeng Zhang , Cheng Chi , Yongqiang Yao , Zhen Lei , Stan Z. Li

RLHF has emerged as a predominant approach for aligning artificial intelligence systems with human preferences, demonstrating exceptional and measurable efficacy in instruction following tasks; however, it exhibits insufficient compliance…

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

Alignment of Large Language Models (LLMs) aims to align outputs with human preferences, and personalized alignment further adapts models to individual users. This relies on personalized reward models that capture user-specific preferences…

Computation and Language · Computer Science 2026-04-21 Hongru Cai , Yongqi Li , Tiezheng Yu , Fengbin Zhu , Wenjie Wang , Fuli Feng , Wenjie Li

The Bradley-Terry (BT) model is widely practiced in reward modeling for reinforcement learning with human feedback (RLHF). Despite its effectiveness, reward models (RMs) trained with BT model loss are prone to over-optimization, losing…

Computation and Language · Computer Science 2025-05-13 Jiwoo Hong , Noah Lee , Eunki Kim , Guijin Son , Woojin Chung , Aman Gupta , Shao Tang , James Thorne

In reinforcement learning from human feedback, preference-based reward models play a central role in aligning large language models to human-aligned behavior. However, recent studies show that these models are prone to reward hacking and…

Artificial Intelligence · Computer Science 2025-10-23 Wenqian Ye , Guangtao Zheng , Aidong Zhang

We study the problem of online multi-agent reinforcement learning (MARL) in environments with sparse rewards, where reward feedback is not provided at each interaction but only revealed at the end of a trajectory. This setting, though…

Machine Learning · Computer Science 2025-09-29 The Viet Bui , Tien Mai , Hong Thanh Nguyen

Reward modeling has emerged as a promising approach for the scalable alignment of language models. However, contemporary reward models (RMs) often lack robustness, awarding high rewards to low-quality, out-of-distribution (OOD) samples.…

Reinforcement learning from human feedback (RLHF) is the mainstream paradigm used to align large language models (LLMs) with human preferences. Yet existing RLHF heavily relies on accurate and informative reward models, which are vulnerable…

Computation and Language · Computer Science 2024-03-15 Wei Shen , Xiaoying Zhang , Yuanshun Yao , Rui Zheng , Hongyi Guo , Yang Liu

Biological agents have meaningful interactions with their environment despite the absence of immediate reward signals. In such instances, the agent can learn preferred modes of behaviour that lead to predictable states -- necessary for…

Artificial Intelligence · Computer Science 2021-07-20 Noor Sajid , Panagiotis Tigas , Alexey Zakharov , Zafeirios Fountas , Karl Friston

As Large Language Models (LLMs) continue to progress toward more advanced forms of intelligence, Reinforcement Learning from Human Feedback (RLHF) is increasingly seen as a key pathway toward achieving Artificial General Intelligence (AGI).…

Machine Learning · Computer Science 2024-10-17 Yuzi Yan , Xingzhou Lou , Jialian Li , Yiping Zhang , Jian Xie , Chao Yu , Yu Wang , Dong Yan , Yuan Shen

Reinforcement learning agents are fundamentally limited by the quality of the reward functions they learn from, yet reward design is often overlooked under the assumption that a well-defined reward is readily available. However, in…

Every RLHF-trained language model is shaped by a reward model, yet the mechanistic interpretability toolkit -- logit lens, direct logit attribution, activation patching, sparse autoencoders -- was built for generative LLMs whose primitives…

Machine Learning · Computer Science 2026-04-30 Mohammed Suhail B Nadaf

Reward modeling is central to alignment pipelines such as RLHF, RLAIF, and PPO-based policy optimization, yet its reliability is constrained by limited and heterogeneous human preference data that are expensive to collect at scale. While…

Machine Learning · Computer Science 2026-05-26 Payel Bhattacharjee , Osvaldo Simeone , Ravi Tandon

Humans use social context to specify preferences over behaviors, i.e. their reward functions. Yet, algorithms for inferring reward models from preference data do not take this social learning view into account. Inspired by pragmatic human…

Machine Learning · Computer Science 2024-05-24 Andi Peng , Yuying Sun , Tianmin Shu , David Abel

A central belief in scaling reinforcement learning with verifiable rewards for instruction following (IF) tasks is that, a diverse mixture of verifiable hard and unverifiable soft constraints is essential for generalizing to unseen…

Machine Learning · Computer Science 2026-01-14 Yirong Zeng , Yufei Liu , Xiao Ding , Yutai Hou , Yuxian Wang , Haonan Song , Wu Ning , Dandan Tu , Qixun Zhang , Bibo Cai , Yuxiang He , Ting Liu

Prior work in multi-objective reinforcement learning typically uses linear reward scalarization with fixed weights, which provably fails to capture non-convex Pareto fronts and thus yields suboptimal results. This limitation becomes…

Machine Learning · Computer Science 2026-04-01 Yining Lu , Zilong Wang , Shiyang Li , Xin Liu , Changlong Yu , Qingyu Yin , Zhan Shi , Zixuan Zhang , Meng Jiang