The Null Token Knows: Reducing Message-Free Hallucination in ASR and NMT

Excerpt

arXiv:2608.15940v1 Announce Type: cross Abstract: Modern encoder-decoder systems can produce fluent text even when their input contains no recoverable message. We study this failure in ASR and NMT through the models' reserved null tokens, asking whether the score for ending generation already carries a usable abstention signal. Across speech recognizers and translation models, we audit native null-token scores and scalar logit shifts. In Whisper, we additionally probe decoder states and compare