Fine-Tuning Language Models from Human Preferences

by   Daniel M. Ziegler, et al.

Reward learning enables the application of reinforcement learning (RL) to tasks where reward is defined by human judgment, building a model of reward by asking humans questions. Most work on reward learning has used simulated environments, but complex information about values is often expressed in natural language, and we believe reward learning for language is a key to making RL practical and safe for real-world tasks. In this paper, we build on advances in generative pretraining of language models to apply reward learning to four natural language tasks: continuing text with positive sentiment or physically descriptive language, and summarization tasks on the TL;DR and CNN/Daily Mail datasets. For stylistic continuation we achieve good results with only 5,000 comparisons evaluated by humans. For summarization, models trained with 60,000 comparisons copy whole sentences from the input but skip irrelevant preamble; this leads to reasonable ROUGE scores and very good performance according to our human labelers, but may be exploiting the fact that labelers rely on simple heuristics.


page 8

page 10


Learning to summarize from human feedback

As language models become more powerful, training and evaluation are inc...

Training Language Models with Natural Language Feedback

Pretrained language models often do not perform tasks in ways that are i...

A Narration-based Reward Shaping Approach using Grounded Natural Language Commands

While deep reinforcement learning techniques have led to agents that are...

A Survey of Reinforcement Learning Informed by Natural Language

To be successful in real-world tasks, Reinforcement Learning (RL) needs ...

RL with KL penalties is better viewed as Bayesian inference

Reinforcement learning (RL) is frequently employed in fine-tuning large ...

Deep Reinforcement Learning with Distributional Semantic Rewards for Abstractive Summarization

Deep reinforcement learning (RL) has been a commonly-used strategy for t...

Uncertainty Estimation for Language Reward Models

Language models can learn a range of capabilities from unsupervised trai...