English
Related papers

Related papers: Theoretical Limits of Language Model Alignment

200 papers

Despite notable advancements in Multimodal Large Language Models (MLLMs), most state-of-the-art models have not undergone thorough alignment with human preferences. This gap exists because current alignment research has primarily achieved…

Reinforcement learning from human feedback (RLHF) aligns large language models (LLMs) by encouraging their generations to have high rewards, using a reward model trained on human preferences. To prevent the forgetting of pre-trained…

The alignment of large language models (LLMs) with human preferences is commonly achieved through Reinforcement Learning from Human Feedback (RLHF). Direct Preference Optimization (DPO) simplified this paradigm by establishing a direct…

Machine Learning · Computer Science 2025-09-26 Yuandong Tan

Reward design plays a pivotal role in aligning large language models (LLMs) with human values, serving as the bridge between feedback signals and model optimization. This survey provides a structured organization of reward modeling and…

Computation and Language · Computer Science 2025-09-03 Miaomiao Ji , Yanqiu Wu , Zhibin Wu , Shoujin Wang , Jian Yang , Mark Dras , Usman Naseem

Collecting high-quality preference datasets for reinforcement learning from human feedback (RLHF) is resource-intensive and challenging. As a result, researchers often train reward models on extensive offline datasets which aggregate…

Machine Learning · Computer Science 2024-12-17 Shambhavi Krishna , Aishwarya Sahoo

Reward models play a key role in aligning language model applications towards human preferences. However, this setup creates an incentive for the language model to exploit errors in the reward model to achieve high estimated reward, a…

Alignment and adaptation in large language models heavily rely on reinforcement learning from human feedback (RLHF); yet, theoretical understanding of its generalisability remains premature, especially when the learned reward could shift,…

Machine Learning · Computer Science 2026-02-26 Kenton Tang , Yuzhu Chen , Fengxiang He

Aligning the behavior of Large language models (LLMs) with human intentions and values remains a critical challenge. Reinforcement learning from human feedback (RLHF) aligns LLMs by training a reward model (RM) on human preferences and…

Computation and Language · Computer Science 2025-12-25 Jiayi Zhou , Jiaming Ji , Juntao Dai , Dong Li , Yaodong Yang

Reinforcement learning with verifiable rewards (RLVR) has become a standard approach for improving reasoning in language models, yet models trained with RLVR often suffer from diversity collapse: while single-sample accuracy improves,…

Machine Learning · Computer Science 2026-05-05 Marc Dymetman

Reinforcement Learning from Human Feedback (RLHF) has been crucial to the recent success of Large Language Models (LLMs), however, it is often a complex and brittle process. In the classical RLHF framework, a reward model is first trained…

Machine Learning · Computer Science 2024-11-06 Rafael Rafailov , Yaswanth Chittepu , Ryan Park , Harshit Sikchi , Joey Hejna , Bradley Knox , Chelsea Finn , Scott Niekum

Aligning large language models (LLMs) with human preferences through reinforcement learning (RLHF) can lead to reward hacking, where LLMs exploit failures in the reward model (RM) to achieve seemingly high rewards without meeting the…

Machine Learning · Computer Science 2024-01-23 Alexandre Ramé , Nino Vieillard , Léonard Hussenot , Robert Dadashi , Geoffrey Cideron , Olivier Bachem , Johan Ferret

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

Large Language Models (LLMs) are nowadays expected to generate content aligned with human preferences. Current work focuses on alignment at model training time, through techniques such as Reinforcement Learning with Human Feedback (RLHF).…

Artificial Intelligence · Computer Science 2026-01-21 James Y. Huang , Sailik Sengupta , Daniele Bonadiman , Yi-An Lai , Arshit Gupta , Nikolaos Pappas , Saab Mansour , Katrin Kirchhoff , Dan Roth

Large language models (LLMs) have shown promise in performing complex multi-step reasoning, yet they continue to struggle with mathematical reasoning, often making systematic errors. A promising solution is reinforcement learning (RL)…

Machine Learning · Computer Science 2025-09-22 Hanning Zhang , Pengcheng Wang , Shizhe Diao , Yong Lin , Rui Pan , Hanze Dong , Dylan Zhang , Pavlo Molchanov , Tong Zhang

A safe and trustworthy use of Large Language Models (LLMs) requires an accurate expression of confidence in their answers. We propose a novel Reinforcement Learning approach that allows to directly fine-tune LLMs to express calibrated…

Computation and Language · Computer Science 2026-03-03 David Bani-Harouni , Chantal Pellegrini , Paul Stangel , Ege Özsoy , Kamilia Zaripova , Nassir Navab , Matthias Keicher

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

Alignment of large language models (LLMs) typically involves training a reward model on preference data, followed by policy optimization with respect to the reward model. However, optimizing policies with respect to a single reward model…

Machine Learning · Computer Science 2025-07-23 Debangshu Banerjee , Kintan Saha , Aditya Gopalan

Mathematical reasoning is a key benchmark for large language models. Reinforcement learning is a standard post-training mechanism for improving the reasoning capabilities of large language models, yet performance remains sensitive to the…

Computation and Language · Computer Science 2026-05-11 Arash Ahmadi , Sarah Sharif , Yaser , Banad

Reinforcement Learning from Human Feedback (RLHF) has become a popular approach to align language models (LMs) with human preferences. This method involves collecting a large dataset of human pairwise preferences across various text…

Machine Learning · Computer Science 2024-10-24 Antoine Scheid , Etienne Boursier , Alain Durmus , Michael I. Jordan , Pierre Ménard , Eric Moulines , Michal Valko

The widespread application of large language models (LLMs) raises increasing demands on ensuring safety or imposing constraints, such as reducing harmful content and adhering to predefined rules. While there have been several works studying…

Machine Learning · Computer Science 2026-02-13 Yihan Du , Seo Taek Kong , R. Srikant