SOURCE-LINKED INTELLIGENCE

Overfitting Mitigation via Singular Value Decomposition in Minimum Bayes Risk Decoding

arXiv · AI, language, vision and robotics · article · Sep 1, 2026 · UTC

Minimum Bayes Risk (MBR) decoding enables high-quality text generation by selecting the hypothesis that maximizes a utility metric over sampled pseudo-references. However, it is highly susceptible to metric overfitting: it can irregularly inflate the chosen utility metric at the direct expense of other unoptimized evaluation metrics. To mitigate this, we introduce SVD-MBR, which frames the pairwise utility matrix as a noisy information signal. By computing a low-rank approximation via Singular Value Decomposition (SVD) and retaining only the top-$k$ components, we effectively decouple true con

Read original source ↗ Open in workspace

recordType

paper

region

Global