No AI summary available for this article.
Why It Matters
Minimum Bayes Risk (MBR) decoding enables high-quality text generation by selecting the hypothesis that maximizes a utility metric over sampled pseudo-references.
Provenance
Discovered via ArXiv and published by ArXiv.
Key Claims
Original description
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...
Discovered via ArXiv
Research papers and preprints from arXiv.
Publisher: arxiv.org
ID: http://arxiv.org/abs/2609.01135v1 · Indexed about 2 hours ago