On the True Distribution Approximation of Minimum Bayes-Risk Decoding
CoRR(2024)
摘要
Minimum Bayes-risk (MBR) decoding has recently gained renewed attention in
text generation. MBR decoding considers texts sampled from a model as
pseudo-references and selects the text with the highest similarity to the
others. Therefore, sampling is one of the key elements of MBR decoding, and
previous studies reported that the performance varies by sampling methods. From
a theoretical standpoint, this performance variation is likely tied to how
closely the samples approximate the true distribution of references. However,
this approximation has not been the subject of in-depth study. In this study,
we propose using anomaly detection to measure the degree of approximation. We
first closely examine the performance variation and then show that previous
hypotheses about samples do not correlate well with the variation, but our
introduced anomaly scores do. The results are the first to empirically support
the link between the performance and the core assumption of MBR decoding.
更多查看译文
AI 理解论文
溯源树
样例
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要