ARGS: Alignment as Reward-Guided Search

Maxim Khanov, Jirayu Burapacheep, Yixuan Li

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: Alignment, LLM

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

Abstract: 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 Search, a novel framework that integrates alignment into the decoding process, eliminating the need for expensive RL training. By adjusting the model’s probabilistic predictions using a reward signal, ARGS generates texts with semantic diversity while being aligned with human preferences, offering a promising and flexible solution for aligning language models. Notably, our method demonstrates consistent enhancements in average reward compared to baselines across diverse alignment tasks and various model dimensions. For example, under the same greedy-based decoding strategy, our method improves the average reward by 19.56% relative to the baseline and secures a preference or tie score of 64.33% in GPT-4 evaluation. We believe that our framework, emphasizing test-time alignment, paves the way for more responsive language models in the future. Code is publicly available at: https://github.com/deeplearning-wisc/args.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Primary Area: societal considerations including fairness, safety, privacy

Submission Number: 2603