SteerLM: Attribute Conditioned SFT as an (User-Steerable) Alternative to RLHF

Yi Dong, Zhilin Wang, Makesh Narsimhan Sreedhar, Xianchao Wu, Oleksii Kuchaiev

Submission Type: Regular Long Paper

Submission Track: Theme Track: Large Language Models and the Future of NLP

Submission Track 2: Language Modeling and Analysis of Language Models

Keywords: Steerable AI, Large Language Model, Alignment, Supervised Fine-tuning

TL;DR: User-customizable Model Alignment based on Supervised Fine-tuning, providing a competitive alternative to RLHF

Abstract: Model alignment with human preferences is an essential step in making Large Language Models (LLMs) helpful and consistent with human values. It typically consists of supervised fine-tuning (SFT) and reinforcement learning from human feedback (RLHF) stages. However, RLHF faces inherent limitations stemming from a complex training setup and its tendency to align the model with implicit values that end users cannot control at run-time. Moreover, reward models in RLHF stage commonly rely on single-dimensional feedback as opposed to explicit, multifaceted signals that indicate attributes such as helpfulness, humor, and toxicity. To address these limitations, we propose SteerLM, a supervised fine-tuning method that empowers end-users to control responses during inference. SteerLM conditions responses to conform to an explicitly defined multi-dimensional set of attributes, thereby empowering a steerable AI capable of generating helpful and high-quality responses while maintaining customizability. Experiments show that SteerLM trained on open source datasets generates responses that are preferred by human and automatic evaluators to many state-of-the-art baselines trained with RLHF while being much easier to train. Try SteerLM at https://huggingface.co/nvidia/SteerLM-llama2-13B

Submission Number: 1165