Noisy-Channel Minimum Bayes Risk Decoding

2026-07-06

AI Summary

This work addresses the limitation of traditional Minimum Bayes Risk (MBR) decoding, which overlooks the bidirectional relationship between hypotheses and reference texts when employing asymmetric evaluation metrics. The authors introduce, for the first time, a noisy channel model into the MBR framework, decomposing the risk into four components: the likelihoods of “hypothesis→reference” and “reference→hypothesis” directions along with their respective priors. This formulation explicitly models metric asymmetry and provides a unified interpretation of existing MBR variants. By integrating Bayesian inference, pseudo-reference sampling, and expectation computation over metrics such as BLEU and COMET, the method achieves channel-level interpretability and flexible weighting. Experiments demonstrate consistent contributions across channels in diverse tasks, with properly weighted combinations significantly outperforming standard MBR decoding.

Abstract

Minimum Bayes Risk (MBR) decoding yields more robust and higher-quality text generation than maximum a posteriori (MAP) decoding by selecting hypotheses that maximize expected utility over sampled pseudo-references. However, there exists a discrepancy in the design: hypothesis selection calculates expected utility scores conditioned on given pseudo-references, while commonly used evaluation metrics, e.g., BLEU and COMET, are asymmetric. Therefore, it is important to consider both hypothesis-to-reference and reference-to-hypothesis directional effects. In this study, we introduce a noisy channel decomposition of MBR decoding that naturally incorporates bidirectional effects to account for these asymmetries. We decompose MBR decoding into four interacting components: hypothesis-to-reference likelihood, reference-to-hypothesis likelihood, hypothesis prior, and reference prior. This decomposition provides a unified interpretation of existing MBR variants and enables metric- and task-specific interpretability by isolating the contribution of each channel. Our comprehensive analysis reveals that channel-wise contributions exhibit distinct characteristics across metrics while remaining consistent across tasks, and suggests that appropriate channel weighting may lead to improvements over original MBR decoding.

Problem

• Minimum Bayes Risk
• Noisy-Channel
• Asymmetric Evaluation Metrics
• Text Generation
• Decoding

Innovation

• Noisy-Channel Decomposition
• Minimum Bayes Risk Decoding
• Bidirectional Evaluation
• Hypothesis-Reference Asymmetry
• Channel-wise Interpretability