Minimum Bayes-risk automatic speech recognition
PulseAugur coverage of Minimum Bayes-risk automatic speech recognition — every cluster mentioning Minimum Bayes-risk automatic speech recognition across labs, papers, and developer communities, ranked by signal.
-
New C-GRPO method optimizes text generation, reducing inference costs
Researchers have introduced Consensus Group Relative Policy Optimization (C-GRPO), a novel method for text generation that aims to reduce computational costs associated with sample-and-rerank decoding. Unlike previous a…
-
New SVD-MBR method combats overfitting in text generation
Researchers have developed a new method called SVD-MBR to combat overfitting in Minimum Bayes Risk (MBR) decoding for text generation. This technique uses Singular Value Decomposition (SVD) to approximate the utility ma…
-
LLM-powered SymCA framework enhances interpretable column annotation
Researchers have developed SymCA, a novel framework for column annotation that utilizes Large Language Models (LLMs) to create an interpretable, symbolic decision process. This approach addresses limitations in existing…
-
New MBR decoding approach incorporates bidirectional effects for improved text generation
Researchers have introduced a novel noisy channel decomposition for Minimum Bayes Risk (MBR) decoding, aiming to improve text generation quality. This approach addresses the asymmetry in common evaluation metrics like B…