Uncertainty-Aware Decoding with Minimum Bayes' Risk
Keywords: mbr, uncertainty, llms, decoding, machine translation, language generation, variational learning
TL;DR: We generalize MBR into an uncertainty-aware decoding method.
Abstract: Despite their outstanding performance in the majority of scenarios, contemporary
language models still occasionally produce undesirable outputs, for example, hallucinated text. While such behaviors have previously been linked to uncertainty,
there is a notable lack of methods that actively consider uncertainty during text
generation. In this work, we show how Minimum Bayes’ Risk (MBR) decoding, a
method that was originally designed to account for the imperfect nature of probabilistic language models, can be generalized into a principled uncertainty-aware
decoding method. In short, we account for model uncertainty during decoding
by incorporating a posterior over model parameters into MBR’s computation of
expected risk. We show that this modified expected risk is useful for both choosing
outputs and deciding when to abstain from generation. We benchmark different
methods for learning posteriors and show that performance correlates with the
diversity of the combined set of models’ predictions.
Primary Area: probabilistic methods (Bayesian methods, variational inference, sampling, UQ, etc.)
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.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
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.
Submission Number: 1172
Loading