cd/entity/Direct Preference Optimization· home› entities› Direct Preference Optimization

grep -l @direct preference optimization /news/*.json | wc -l → 1

@Direct Preference Optimization

mentions 1 type Person feed RSS

04:00

2026-05-26

arxiv.org

large-language-models

Direct Preference Optimization for English-Mandarin Code-Switching Speech Recognition in Audio LLMs

Researchers have identified three systematic failure modes in Audio LLMs when transcribing English-Mandarin code-switching speech: language omission, translation-instead-of-transcription, and hallucin…

// co-occurs with top 2 entities

Audio LLMs 1 English-Mandarin 1