Metraipolis › archive › dc_fe7b7ea9eb29

Listen, Reason, and Segment: Aligning LALMs with Editorial Judgment for Media Chapterization — arXiv:2608.16539

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.16539
License (as archived)
CC0-1.0
Archived
2026-10-18T18:07:20.258Z
SHA-256 of the archived text
356df464223a3cd1e74e9f6aff27cb1a5522df76ad6dbcc18cbc63119f3ad663
Stable URL of this page
https://metraipolis.com/documento/dc_fe7b7ea9eb29

How to cite

Listen, Reason, and Segment: Aligning LALMs with Editorial Judgment for Media Chapterization — arXiv:2608.16539 — arXiv (en), https://arxiv.org/abs/2608.16539 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fe7b7ea9eb29 (Metraipolis archive dc_fe7b7ea9eb29, sha256 356df464223a3cd1e74e9f6aff27cb1a5522df76ad6dbcc18cbc63119f3ad663)
BibTeX
@misc{dcfe7b7ea9eb29,
  title = {Listen, Reason, and Segment: Aligning LALMs with Editorial Judgment for Media Chapterization — arXiv:2608.16539},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.16539},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fe7b7ea9eb29; sha256 356df464223a3cd1e74e9f6aff27cb1a5522df76ad6dbcc18cbc63119f3ad663},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.16539. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large Audio Language Models (LALMs) have made rapid progress on standardized benchmarks, yet their deployment in practical media workflows, curation, archival indexing, and content distribution remains largely unrealized. We identify automated audio chapterization, the task of segmenting continuous audio streams into thematically coherent chapters, as a demanding and commercially consequential setting that exposes this gap. Chapterization is challenging because boundaries are defined less by objective acoustic events than by subjective editorial judgment, requiring models to reason sequentially over long acoustic contexts and approximate creator-authored boundary decisions. We present AudioChaps, a post-training framework for aligning end-to-end LALMs for this task via Group Relative Policy Optimization (GRPO) guided by Chain-of-Thought (CoT) reasoning. To support training and evaluation, we curate three datasets: AudioChaps-Alignment, derived from creator-annotated chapter boundaries on YouTube; AudioChaps-CoT, which provides structured supervision for well-formatted, high-quality, and evidence-grounded boundary reasoning; and AudioChaps-Eval, a held-out benchmark for audio chapterization. Applying GRPO directly without a Supervised Fine-Tuning (SFT) cold start, AudioChaps-R1-Zero already improves average F1 by 33 points over the state-of-the-art LALM Audio-Flamingo-3-Think. The AudioChaps framework produces our final aligned LALM, AudioChaps-R1, which improves average F1 by 49 points. These results demonstrate that GRPO-trained LALMs can reliably transform unstructured auditory streams into navigable, structured media. Our code, models, and dataset resources will be released upon acceptance at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI).
Categorie arXiv: Sound (cs.SD) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Audio and Speech Processing (eess.AS).
Pagina del lavoro: https://arxiv.org/abs/2608.16539 — 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 2026-10-18T16:29:14.128Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).