English
Related papers

Related papers: The Effect of Modeling Human Rationality Level on …

200 papers

Reward modeling is essential for aligning large language models with human preferences through reinforcement learning. To provide accurate reward signals, a reward model (RM) should stimulate deep thinking and conduct interpretable…

Computation and Language · Computer Science 2026-03-09 Xiusi Chen , Gaotang Li , Ziqi Wang , Bowen Jin , Cheng Qian , Yu Wang , Hongru Wang , Yu Zhang , Denghui Zhang , Tong Zhang , Hanghang Tong , Heng Ji

When robots enter everyday human environments, they need to understand their tasks and how they should perform those tasks. To encode these, reward functions, which specify the objective of a robot, are employed. However, designing reward…

Robotics · Computer Science 2022-10-21 Erdem Bıyık

Reinforcement Learning from Human feedback (RLHF) has become a powerful tool to fine-tune or train agentic machine learning models. Similar to how humans interact in social contexts, we can use many types of feedback to communicate our…

Machine Learning · Computer Science 2025-02-21 Yannick Metz , David Lindner , Raphaël Baur , Mennatallah El-Assady

Learning from human feedback has gained traction in fields like robotics and natural language processing in recent years. While prior works mostly rely on human feedback in the form of comparisons, language is a preferable modality that…

Robotics · Computer Science 2024-10-10 Zhaojing Yang , Miru Jun , Jeremy Tien , Stuart J. Russell , Anca Dragan , Erdem Bıyık

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 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

When developing new large language models (LLMs), a key step is evaluating their final performance, often by computing the win-rate against a reference model based on external feedback. Human feedback is the gold standard, particularly for…

Machine Learning · Computer Science 2025-02-26 Zhaoyi Zhou , Yuda Song , Andrea Zanette

Human annotation is central to NLP evaluation, yet subjective tasks often exhibit substantial variability across annotators. While large language models (LLMs) can provide structured reasoning to support annotation, their influence on human…

Computation and Language · Computer Science 2026-04-17 Smitha Muthya Sudheendra , Jaideep Srivastava

Integration of human feedback plays a key role in improving the learning capabilities of intelligent systems. This comparative study delves into the performance, robustness, and limitations of imitation learning compared to traditional…

Machine Learning · Computer Science 2024-10-30 Amr Gomaa , Bilal Mahdy

Learning about many things can provide numerous benefits to a reinforcement learning system. For example, learning many auxiliary value functions, in addition to optimizing the environmental reward, appears to improve both exploration and…

Machine Learning · Computer Science 2020-08-25 Cam Linke , Nadia M. Ady , Martha White , Thomas Degris , Adam White

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

Reinforcement Learning from Human Feedback significantly enhances Natural Language Processing by aligning language models with human expectations. A critical factor in this alignment is the strength of reward models used during training.…

Computation and Language · Computer Science 2024-10-17 Yanjun Chen , Dawei Zhu , Yirong Sun , Xinghao Chen , Wei Zhang , Xiaoyu Shen

Conveying complex objectives to reinforcement learning (RL) agents can often be difficult, involving meticulous design of reward functions that are sufficiently informative yet easy enough to provide. Human-in-the-loop RL methods allow…

Machine Learning · Computer Science 2021-06-10 Kimin Lee , Laura Smith , Pieter Abbeel

Reinforcement Learning from Human Feedback has recently achieved significant success in various fields, and its performance is highly related to feedback quality. While much prior work acknowledged that human teachers' characteristics would…

Robotics · Computer Science 2025-12-30 Qidi Fang , Hang Yu , Shijie Fang , Jindan Huang , Qiuyu Chen , Reuben M. Aronson , Elaine S. Short

Language models (LMs) often exhibit undesirable text generation behaviors, including generating false, toxic, or irrelevant outputs. Reinforcement learning from human feedback (RLHF) - where human preference judgments on LM outputs are…

Computation and Language · Computer Science 2023-10-31 Zeqiu Wu , Yushi Hu , Weijia Shi , Nouha Dziri , Alane Suhr , Prithviraj Ammanabrolu , Noah A. Smith , Mari Ostendorf , Hannaneh Hajishirzi

Reinforcement Learning with Verifiable reward (RLVR) on preference data has become the mainstream approach for training Generative Reward Models (GRMs). Typically in pairwise rewarding tasks, GRMs generate reasoning chains ending with…

Computation and Language · Computer Science 2026-05-04 Zongqi Wang , Rui Wang , Yuchuan Wu , Yiyao Yu , Pinyi Zhang , Shaoning Sun , Yujiu Yang , Yongbin Li

Learning from human feedback has shown success in aligning large, pretrained models with human values. Prior works have mostly focused on learning from high-level labels, such as preferences between pairs of model outputs. On the other…

Computation and Language · Computer Science 2024-05-24 Amber Xie , Chin-Yi Cheng , Forrest Huang , Yang Li

Multimodal reward models are crucial for aligning multimodal large language models with human preferences. Recent works have incorporated reasoning capabilities into these models, achieving promising results. However, training these models…

Artificial Intelligence · Computer Science 2026-02-03 Shidong Yang , Tongwen Huang , Hao Wen , Yong Wang , Li Chen , Xiangxiang Chu

Learning from human feedback has shown to be a useful approach in acquiring robot reward functions. However, expert feedback is often assumed to be drawn from an underlying unimodal reward function. This assumption does not always hold…

Machine Learning · Computer Science 2021-10-20 Vivek Myers , Erdem Bıyık , Nima Anari , Dorsa Sadigh

Training language models via reinforcement learning often relies on imperfect proxy rewards, since ground truth rewards that precisely define the intended behavior are rarely available. Standard metrics for assessing the quality of proxy…

Machine Learning · Computer Science 2026-04-29 Shuning Shang , Hubert Strauss , Stanley Wei , Sanjeev Arora , Noam Razin