cs.SDNov 19, 2026

When Sounds Turn Heads: Recovering Event Timing That Audio LLMs Fail to Say

Authors: Jongbhin Woo, Jaewook Jeong, Joon Son Chung

Organizations: KAIST

Abstract

Audio LLMs can know when a queried sound occurs but fail to say it. We find a few attention heads that track the queried sound: they shift when the query changes, follow the sound when it moves, and removing or blocking them often hurts the model's timestamps. Yet the answer does not express what they track. Intervals read directly from these heads outperform the model's original answer and recover events that its timestamps miss. To bring this timing into the answer, we introduce head-guided decoding, which needs no training. It keeps the model's decision on whether the sound is present and rescores its candidate timestamps with a prior from these heads. Heads selected on development data transfer unchanged to new recordings and free-text queries, where head-guided decoding improves the timestamps of three audio LLMs, scores above their head readout on every benchmark, and, in most settings, outperforms random-head guidance. On recordings released after the models were trained, head-guided decoding raises mIoU from 0.07-0.36 to 0.48-0.56. These results suggest that poor temporal answers in audio LLMs partly reflect a failure to say rather than to hear, and that the model's own attention can close part of this gap.

Figures & tables

Explore similar work

CardsList
  1. GigaChat Audio: Time-aware Large Audio Language Model

    Jul 11, 2026Aleksandr Kutsakov, Mariia Sadovina, Georgii Gospodinov +4Audio QAAudio Understanding

  2. Tracing Audio Grounding and Answer Selection in Audio LLMs

    Sep 4, 2026Hyebin Cho, Suho Yoo, Jihoo Jung +1Audio-Language ModelsAudio QA

  3. Event-Grounded Question Answering over Long Audio via Structured Retrieval

    Feb 16, 2026Kartik Hegde, Arvind Krishna Sridhar, Naveen Vakada +2Audio UnderstandingAudio QA