English
Related papers

Related papers: How RLHF Amplifies Sycophancy

200 papers

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

Reward modeling is crucial for aligning large language models with human preferences, yet current approaches lack a principled mathematical framework for leveraging ordinal preference data. When human annotators provide graded preferences…

Machine Learning · Computer Science 2026-03-04 Amirhossein Afsharrad , Ruida Zhou , Luca Viano , Sanjay Lall , Mohammad Ghavamzadeh

Preference-based feedback is important for many applications in machine learning where evaluation of a reward function is not feasible. Notable recent examples arise in preference alignment for large language models, including in…

Reinforcement learning from human feedback (RLHF) has emerged as a key enabling technology for aligning AI behaviour with human preferences. The traditional way to collect data in RLHF is via pairwise comparisons: human raters are asked to…

Machine Learning · Computer Science 2025-12-01 Jan Kompatscher , Danqing Shi , Giovanna Varni , Tino Weinkauf , Antti Oulasvirta

The demand for regulating potentially risky behaviors of large language models (LLMs) has ignited research on alignment methods. Since LLM alignment heavily relies on reward models for optimization or evaluation, neglecting the quality of…

Computation and Language · Computer Science 2024-10-01 Yan Liu , Xiaoyuan Yi , Xiaokang Chen , Jing Yao , Jingwei Yi , Daoguang Zan , Zheng Liu , Xing Xie , Tsung-Yi Ho

We investigate Reinforcement Learning from Human Feedback (RLHF) in the context of a general preference oracle. In particular, we do not assume the existence of a reward function and an oracle preference signal drawn from the Bradley-Terry…

Machine Learning · Computer Science 2024-11-13 Chenlu Ye , Wei Xiong , Yuheng Zhang , Hanze Dong , Nan Jiang , Tong Zhang

Reinforcement Learning from Human Feedback (RLHF) facilitates the alignment of large language models with human preferences, significantly enhancing the quality of interactions between humans and models. InstructGPT implements RLHF through…

Computation and Language · Computer Science 2023-10-10 Zheng Yuan , Hongyi Yuan , Chuanqi Tan , Wei Wang , Songfang Huang , Fei Huang

Recent advances in generative AI have been driven by alignment techniques such as reinforcement learning from human feedback (RLHF). RLHF and related techniques typically involve constructing a dataset of binary or ranked choice human…

Machine Learning · Computer Science 2025-04-01 Kailas Vodrahalli , Wei Wei , James Zou

Reinforcement learning has shown remarkable performance in aligning language models with human preferences, leading to the rise of attention towards developing RLHF platforms. These platforms enable users to fine-tune models without…

Machine Learning · Computer Science 2025-03-06 Erfan Entezami , Ali Naseh

Standard practice within Reinforcement Learning from Human Feedback (RLHF) involves optimizing against a Reward Model (RM), which itself is trained to reflect human preferences for desirable generations. A notable subject that is…

Computation and Language · Computer Science 2023-09-29 Lingfeng Shen , Sihao Chen , Linfeng Song , Lifeng Jin , Baolin Peng , Haitao Mi , Daniel Khashabi , Dong Yu

Reward-model-based fine-tuning is a central paradigm in aligning Large Language Models with human preferences. However, such approaches critically rely on the assumption that proxy reward models accurately reflect intended supervision, a…

Computation and Language · Computer Science 2026-01-21 Zixuan Liu , Siavash H. Khajavi , Guangkai Jiang , Xinru Liu

Reinforcement learning has seen wide success in finetuning large language models to better align with instructions via human feedback. The so-called algorithm, Reinforcement Learning with Human Feedback (RLHF) demonstrates impressive…

Computation and Language · Computer Science 2023-02-13 Tianjun Zhang , Fangchen Liu , Justin Wong , Pieter Abbeel , Joseph E. Gonzalez

Through alignment with human preferences, Large Language Models (LLMs) have advanced significantly in generating honest, harmless, and helpful responses. However, collecting high-quality preference data is a resource-intensive and…

Computation and Language · Computer Science 2024-10-10 Qingxiu Dong , Li Dong , Xingxing Zhang , Zhifang Sui , Furu Wei

In recent years, Large Language Models (LLMs) have witnessed a remarkable surge in prevalence, altering the landscape of natural language processing and machine learning. One key factor in improving the performance of LLMs is alignment with…

Computation and Language · Computer Science 2023-10-17 Keita Saito , Akifumi Wachi , Koki Wataoka , Youhei Akimoto

Reward hacking arises when a model improves a proxy reward by exploiting shortcuts rather than solving the intended task. We study this failure mode through the geometry of reinforcement learning updates in language models and argue that…

Machine Learning · Computer Science 2026-05-26 Wenlong Deng , Jiaji Huang , Kaan Ozkara , Yushu Li , Christos Thrampoulidis , Xiaoxiao Li , Youngsuk Park

Large Language Models (LLMs) are prone to sycophantic behavior, uncritically conforming to user beliefs. As models increasingly condition responses on user-specific context (personality traits, preferences, conversation history), they gain…

Computation and Language · Computer Science 2026-03-03 Sean W. Kelley , Christoph Riedl

Reinforcement Learning from Human Feedback (RLHF) has played a crucial role in the success of large models such as ChatGPT. RLHF is a reinforcement learning framework which combines human feedback to improve learning effectiveness and…

Machine Learning · Computer Science 2023-11-28 Feiyang Han , Yimin Wei , Zhaofeng Liu , Yanxing Qi

Reinforcement Learning with Human Feedback (RLHF) is a methodology designed to align Large Language Models (LLMs) with human preferences, playing an important role in LLMs alignment. Despite its advantages, RLHF relies on human annotators…

Artificial Intelligence · Computer Science 2024-06-21 Jiongxiao Wang , Junlin Wu , Muhao Chen , Yevgeniy Vorobeychik , Chaowei Xiao

Single-axis mitigations of reward-model biases (e.g., reducing proxy reliance on length, sycophancy, or style) can rotate optimization pressure onto correlated proxies rather than eliminate it, a failure mode we call reward bias…

Artificial Intelligence · Computer Science 2026-05-28 Max Lamparth , Daniel Fein , Andreas Haupt , Marcel Hussing , Mykel J. Kochenderfer

Learning from human feedback has been shown to be effective at aligning language models with human preferences. Past work has often relied on Reinforcement Learning from Human Feedback (RLHF), which optimizes the language model using reward…

Computation and Language · Computer Science 2023-05-18 Yao Zhao , Rishabh Joshi , Tianqi Liu , Misha Khalman , Mohammad Saleh , Peter J. Liu
‹ Prev 1 8 9 10 Next ›