Metraipolis › archive › dc_4e39d2ef00b4

Represented but Ignored: A Causal Account of Prosodic Underuse in Audio-Language Models — arXiv:2608.19211

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.19211
License (as archived)
CC0-1.0
Archived
2026-10-18T11:39:09.304Z
SHA-256 of the archived text
94eb1f2fce5fd4b2e69ce62e98c8e220f8cc8986ac14fbc26b06ac810b5b8d95
Stable URL of this page
https://metraipolis.com/documento/dc_4e39d2ef00b4

How to cite

Represented but Ignored: A Causal Account of Prosodic Underuse in Audio-Language Models — arXiv:2608.19211 — arXiv (en), https://arxiv.org/abs/2608.19211 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4e39d2ef00b4 (Metraipolis archive dc_4e39d2ef00b4, sha256 94eb1f2fce5fd4b2e69ce62e98c8e220f8cc8986ac14fbc26b06ac810b5b8d95)
BibTeX
@misc{dc4e39d2ef00b4,
  title = {Represented but Ignored: A Causal Account of Prosodic Underuse in Audio-Language Models — arXiv:2608.19211},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.19211},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4e39d2ef00b4; sha256 94eb1f2fce5fd4b2e69ce62e98c8e220f8cc8986ac14fbc26b06ac810b5b8d95},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.19211. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Human speech is richly expressive, with prosody carrying linguistic and emotional information beyond the lexical content. A capable large audio-language model (audio-LLM) should therefore support expressive speech understanding, not only transcribing what was said but also interpreting how it was said. Yet behavioral evaluations alone cannot reveal why a model fails on prosodic input. An error may reflect loss of acoustic information, incorrect internal interpretation, or failure to use a representation that is already available inside the model. We introduce a stage-specific probe ladder for localizing these failure modes in audio-LLMs. Across four understanding-only audio-LLMs, prosodic information is usually preserved in the audio path and decodable in late LLM states. Yet it is only partially expressed in the model's final response. We test the causal status of this latent representation with targeted hidden-state interventions. Every intervention shifts the answer distribution in the predicted direction, and in most model--task cells a single edit at the relevant layer is sufficient to drive the model toward the suppressed prosodic decision, though this recovery is directional rather than a selective restoration of the correct class. Feature-level analysis further suggests that this recoverable signal can be expressed through a small subspace. Some of the highest-attribution features in this analysis align with acoustic cues known to carry prosodic information. Within the matched-content contrasts we test, these results locate the recurring bottleneck not in perceiving prosody but in using it. Models that hear and correctly represent a prosodic cue can still fail to express it in their answers.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-21 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Sound (cs.SD); Audio and Speech Processing (eess.AS).
Pagina del lavoro: https://arxiv.org/abs/2608.19211 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T11:38:27.884Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).