English
Related papers

Related papers: Decoding-time Realignment of Language Models

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

Reinforcement Learning from Human Feedback (RLHF) is a key method for aligning large language models (LLMs) with human preferences. However, current offline alignment approaches like DPO, IPO, and SLiC rely heavily on fixed preference…

Machine Learning · Computer Science 2024-06-25 Mucong Ding , Souradip Chakraborty , Vibhu Agrawal , Zora Che , Alec Koppel , Mengdi Wang , Amrit Bedi , Furong Huang

Reinforcement Learning from Human Feedback (RLHF) has emerged as a pivotal technique for aligning artificial intelligence systems with human values, achieving remarkable success in fine-tuning large language models. However, existing RLHF…

Machine Learning · Computer Science 2025-03-26 Renpu Liu , Peng Wang , Donghao Li , Cong Shen , Jing Yang

Reinforcement Learning from Human Feedback (RLHF) is the standard method to align Large Language Models (LLMs) with human preferences. In this work, we introduce alignment tampering, a potential vulnerability where the LLM undergoing…

Artificial Intelligence · Computer Science 2026-05-27 Dongyoon Hahm , Dylan Hadfield-Menell , Kimin Lee

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

Reinforcement Learning from Human Feedback (\textbf{RLHF}) has emerged as a dominant approach for aligning LLM outputs with human preferences. Inspired by the success of RLHF, we study the performance of multiple algorithms that learn from…

Great success has been reported using Reinforcement Learning from Human Feedback (RLHF) to align large language models, with open preference datasets enabling wider experimentation, particularly for "helpfulness" in tasks like dialogue and…

Computation and Language · Computer Science 2024-07-12 Prasann Singhal , Tanya Goyal , Jiacheng Xu , Greg Durrett

We study estimation and statistical inference for reward models used in aligning large language models (LLMs). A key component of LLM alignment is reinforcement learning from human feedback (RLHF), where humans compare pairs of…

Machine Learning · Statistics 2025-12-04 Pangpang Liu , Junwei Lu , Will Wei Sun

AI alignment in the shape of Reinforcement Learning from Human Feedback (RLHF) is increasingly treated as a crucial ingredient for high performance large language models. Proximal Policy Optimization (PPO) has been positioned by recent…

Existing approaches to language model alignment often treat safety as a tradeoff against helpfulness, which can lead to unacceptable responses in sensitive domains. To ensure reliable performance in such settings, we propose High-Confidence…

Machine Learning · Computer Science 2025-06-11 Yaswanth Chittepu , Blossom Metevier , Will Schwarzer , Austin Hoag , Scott Niekum , Philip S. Thomas

Pre-trained large-scale language models (LLMs) excel at producing coherent articles, yet their outputs may be untruthful, toxic, or fail to align with user expectations. Current approaches focus on using reinforcement learning with human…

Computation and Language · Computer Science 2024-06-06 Dehong Xu , Liang Qiu , Minseok Kim , Faisal Ladhak , Jaeyoung Do

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

Finetuning language models with reinforcement learning (RL), e.g. from human feedback (HF), is a prominent method for alignment. But optimizing against a reward model can improve on reward while degrading performance in other areas, a…

Computation and Language · Computer Science 2023-12-14 Michael Noukhovitch , Samuel Lavoie , Florian Strub , Aaron Courville

Reward models trained on human preference data have been proven to effectively align Large Language Models (LLMs) with human intent within the framework of reinforcement learning from human feedback (RLHF). However, current reward models…

Computation and Language · Computer Science 2024-10-24 Rui Yang , Ruomeng Ding , Yong Lin , Huan Zhang , Tong Zhang

Aligning large language models with human objectives is paramount, yet common approaches including RLHF suffer from unstable and resource-intensive training. In response to this challenge, we introduce ARGS, Alignment as Reward-Guided…

Computation and Language · Computer Science 2024-02-06 Maxim Khanov , Jirayu Burapacheep , Yixuan Li

The growing safety concerns surrounding large language models raise an urgent need to align them with diverse human preferences to simultaneously enhance their helpfulness and safety. A promising approach is to enforce safety constraints…

Artificial Intelligence · Computer Science 2024-11-25 Xinmeng Huang , Shuo Li , Edgar Dobriban , Osbert Bastani , Hamed Hassani , Dongsheng Ding

Reinforcement Learning from Human Feedback (RLHF) is a powerful paradigm for aligning foundation models to human values and preferences. However, current RLHF techniques cannot account for the naturally occurring differences in individual…

Machine Learning · Computer Science 2024-08-20 Sriyash Poddar , Yanming Wan , Hamish Ivison , Abhishek Gupta , Natasha Jaques

Aligning large language models (LLMs) with human preferences is critical to recent advances in generative artificial intelligence. Reinforcement learning from human feedback (RLHF) is widely applied to achieve this objective. A key step in…

Machine Learning · Statistics 2025-01-03 Pangpang Liu , Chengchun Shi , Will Wei Sun

The alignment of large language models (LLMs) with human values is critical as these models become increasingly integrated into various societal and decision-making processes. Traditional methods, such as reinforcement learning from human…

Machine Learning · Computer Science 2025-01-08 Prashant Trivedi , Souradip Chakraborty , Avinash Reddy , Vaneet Aggarwal , Amrit Singh Bedi , George K. Atia

Aligning large language models (LLMs) with human preferences usually requires fine-tuning methods such as RLHF and DPO. These methods directly optimize the model parameters, so they cannot be used in test-time to improve model performance,…

Machine Learning · Computer Science 2025-07-04 Xinnan Zhang , Chenliang Li , Siliang Zeng , Jiaxiang Li , Zhongruo Wang , Kaixiang Lin , Songtao Lu , Alfredo Garcia , Mingyi Hong