Metraipolis › archive › dc_e2c0d63eced3

MuseCritic: Learning Multi-Aspect Song Rewards through Natural-Language Aesthetic Critiques — arXiv:2608.11755

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.11755
License (as archived)
CC0-1.0
Archived
2026-10-19T05:30:59.646Z
SHA-256 of the archived text
e8a3a075e7422e4bbbea993f4f31e0050451e14f21c7a21e8383bdec340f7e1a
Stable URL of this page
https://metraipolis.com/documento/dc_e2c0d63eced3

How to cite

MuseCritic: Learning Multi-Aspect Song Rewards through Natural-Language Aesthetic Critiques — arXiv:2608.11755 — arXiv (en), https://arxiv.org/abs/2608.11755 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e2c0d63eced3 (Metraipolis archive dc_e2c0d63eced3, sha256 e8a3a075e7422e4bbbea993f4f31e0050451e14f21c7a21e8383bdec340f7e1a)
BibTeX
@misc{dce2c0d63eced3,
  title = {MuseCritic: Learning Multi-Aspect Song Rewards through Natural-Language Aesthetic Critiques — arXiv:2608.11755},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.11755},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e2c0d63eced3; sha256 e8a3a075e7422e4bbbea993f4f31e0050451e14f21c7a21e8383bdec340f7e1a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.11755. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Long-form song generation models continue to improve in duration, structural coherence, and acoustic complexity, increasing the need for reliable aesthetic rewards aligned with human preferences. However, reward models for complete songs remain limited, and existing evaluators typically predict scores in a single forward pass without readable explanations. To this end, we introduce MuseCritic, a semi-scalar reward model that generates a natural-language critique covering five aesthetic dimensions and uses it as an intermediate representation to predict continuous reward scores. MuseCritic follows a two-stage training pipeline: a teacher model first provides high-quality critiques for supervised fine-tuning, then the fine-tuned model generates its own critiques for reward learning, mitigating training-inference distribution shift. On an in-domain test set of 200 SongEval songs, MuseCritic reduces macro-averaged mean squared error from 0.2875 to 0.2316 and improves macro-averaged LCC, SRCC, and Kendall's tau to 0.9068, 0.8838, and 0.7178, respectively. On the out-of-domain Music Arena benchmark with 733 preference pairs, it achieves 71.35% accuracy and remains competitive with strong music-specific reward models. Using MuseCritic with GRPO also improves Muse-0.6B on all nine aesthetic metrics from SongEval and Audiobox Aesthetics. These results show that critique-conditioned reward modeling reduces scoring error and provides an effective optimization signal for song generation. The project repository is available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-13 in cs.CL).
Categorie arXiv: Sound (cs.SD) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.11755 — 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 2026-10-19T05:15:39.252Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-13?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).