Metraipolis › archive › dc_89f07e2aaea5

MRMAD: A Multi-Round Multi-Audio Benchmark for Evaluating Acoustic Degradation Perception in Large Audio-Language Models — arXiv:2608.22236

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.22236
License (as archived)
CC0-1.0
Archived
2026-10-18T10:16:17.140Z
SHA-256 of the archived text
6ec7baf365f7b8d1b079fc6f72dcdbd704778e7c80af02e9185771a1c916a086
Stable URL of this page
https://metraipolis.com/documento/dc_89f07e2aaea5

How to cite

MRMAD: A Multi-Round Multi-Audio Benchmark for Evaluating Acoustic Degradation Perception in Large Audio-Language Models — arXiv:2608.22236 — arXiv (en), https://arxiv.org/abs/2608.22236 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_89f07e2aaea5 (Metraipolis archive dc_89f07e2aaea5, sha256 6ec7baf365f7b8d1b079fc6f72dcdbd704778e7c80af02e9185771a1c916a086)
BibTeX
@misc{dc89f07e2aaea5,
  title = {MRMAD: A Multi-Round Multi-Audio Benchmark for Evaluating Acoustic Degradation Perception in Large Audio-Language Models — arXiv:2608.22236},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.22236},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_89f07e2aaea5; sha256 6ec7baf365f7b8d1b079fc6f72dcdbd704778e7c80af02e9185771a1c916a086},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.22236. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large audio-language models (LALMs) have shown promising progress in understanding speech, music, and general sound events, yet their ability to reason about how audio signals are degraded remains underexplored. Existing benchmarks primarily evaluate semantic understanding, event recognition, or high-level audio reasoning, leaving a basic question unanswered: Do LALMs understand the differences in audio quality? We introduce MRMAD, a Multi-Round Multi-Audio Degradation benchmark for evaluating audio degradation perception and understanding in LALMs. MRMAD spans speech, music, and sound, and frames evaluation as multi-turn dialogues across multiple audio inputs, requiring models to identify types of degradation, compare severity, and perceive corruption changes across turns. Unlike current single-turn audio-language benchmarks, MRMAD evaluates whether LALMs can maintain consistent degradation hypotheses with new evidence and comprehend low-level acoustic phenomena over multi-turn dialogues. Through a systematic evaluation of 18 representative LALMs from non-thinking to reasoning and Omni models, we find that current models often recognize coarse content while failing to diagnose, compare, or reason about degradations reliably. Human evaluations further reveal a significant perception gap between LALMs and human listeners. MRMAD thus exposes a critical yet overlooked aspect of audio-language understanding and provides a diagnostic foundation for building future LALMs that are robust to real-world acoustic conditions.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-25 in eess.AS).
Categorie arXiv: Sound (cs.SD) ; Machine Learning (cs.LG); Audio and Speech Processing (eess.AS).
Pagina del lavoro: https://arxiv.org/abs/2608.22236 — 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 2026-10-18T10:09:07.493Z dalla pagina https://arxiv.org/catchup/eess.AS/2026-08-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).