Papers › Aligning Language Models with Offline Learning from Human Feedback

Aligning Language Models with Offline Learning from Human Feedback

23 Aug 2023arXiv:2308.12050archive 2025-07-28

Jian Hu, Li Tao, June Yang, Chandler Zhou

Learning from human preferences is crucial for language models (LMs) to effectively cater to human needs and societal values. Previous research has made notable progress by leveraging human feedback to follow instructions. However, these approaches rely primarily on online learning techniques like Proximal Policy Optimization (PPO), which have been proven unstable and challenging to tune for language models. Moreover, PPO requires complex distributed system implementation, hindering the efficiency of large-scale distributed training. In this study, we propose an offline learning from human feedback framework to align LMs without interacting with environments. Specifically, we explore filtering alignment (FA), reward-weighted regression (RWR), and conditional alignment (CA) to align language models to human preferences. By employing a loss function similar to supervised fine-tuning, our methods ensure more stable model training than PPO with a simple machine learning system~(MLSys) and much fewer (around 9\%) computing resources. Experimental results demonstrate that conditional alignment outperforms other offline alignment methods and is comparable to PPO.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

OpenLLMAI/OpenRLHF officialmentioned on GitHubpytorchApache-2.0 report
openrlhf/openrlhf mentioned on GitHubpytorchApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Reinforcement Learning (RL)reinforcement-learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

ALIGNAbsolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutEntropy RegularizationLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPPOPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections