Improving Minimum Bayes Risk Decoding with Multi-Prompt
While instruction fine-tuned LLMs are effective text generators, sensitivity to prompt construction makes performance unstable and sub-optimal in practice. Relying on a single "best" prompt cannot capture all differing approaches to a generation problem. Using this observation, we propose multi-prompt decoding, where many candidate generations are decoded from a prompt bank at inference-time. To ensemble candidates, we use Minimum Bayes Risk (MBR) decoding, which selects a final output using a trained value metric. We show multi-prompt improves MBR across a comprehensive set of conditional generation tasks, and show this is a result of estimating a more diverse and higher quality candidate space than that of a single prompt. Further experiments confirm multi-prompt improves generation across tasks, models and metrics.
Code (1)
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Generating Diverse and High-Quality Texts by Minimum Bayes Risk Decoding
One of the most important challenges in text generation systems is to produce outputs that are not only correct but also diverse. Recently, Minimum Bayes-Risk (MBR) decoding has gained prominence for generating sentences…
DecoderDiversityLanguage ModelingLanguage Modelling+2Later-stage Minimum Bayes-Risk Decoding for Neural Machine Translation
For extended periods of time, sequence generation models rely on beam search algorithm to generate output sequence. However, the correctness of beam search degrades when the a model is over-confident about a suboptimal p…
GPUMachine TranslationRerankingTranslationDirect Preference Optimization for Neural Machine Translation with Minimum Bayes Risk Decoding
Minimum Bayes Risk (MBR) decoding can significantly improve translation performance of Multilingual Large Language Models (MLLMs). However, MBR decoding is computationally expensive. We show how the recently developed Re…
Machine TranslationNMTreinforcement-learningReinforcement Learning+2Non-Autoregressive Minimum Bayes' Risk Decoding for Fast Speech Recognition
Non-autoregressive (NAR) decoding generates output tokens in parallel, making speech recognition faster than autoregressive decoding, which generates them sequentially from left to right. However, the recognition perform…
Speech RecognitionUnveiling the Power of Source: Source-based Minimum Bayes Risk Decoding for Neural Machine Translation
Maximum a posteriori decoding, a commonly used method for neural machine translation (NMT), aims to maximize the estimated posterior probability. However, high estimated probability does not always lead to high translati…
Machine TranslationNMTRerankingTranslation