Metraipolis › archive › dc_16f549f682fb

CineSubBench: Evaluating LLMs on Long-Form Narrative and Cultural Understanding from Multilingual Movie Subtitles — arXiv:2609.36218

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.36218
License (as archived)
CC0-1.0
Archived
2026-10-07T16:25:29.549Z
SHA-256 of the archived text
6d39c8a23114b4dfaeb32db56bfd5b9fd7451b9feb8d4d38de625bc560b37ed8
Stable URL of this page
https://metraipolis.com/documento/dc_16f549f682fb

How to cite

CineSubBench: Evaluating LLMs on Long-Form Narrative and Cultural Understanding from Multilingual Movie Subtitles — arXiv:2609.36218 — arXiv (en), https://arxiv.org/abs/2609.36218 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_16f549f682fb (Metraipolis archive dc_16f549f682fb, sha256 6d39c8a23114b4dfaeb32db56bfd5b9fd7451b9feb8d4d38de625bc560b37ed8)
BibTeX
@misc{dc16f549f682fb,
  title = {CineSubBench: Evaluating LLMs on Long-Form Narrative and Cultural Understanding from Multilingual Movie Subtitles — arXiv:2609.36218},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.36218},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_16f549f682fb; sha256 6d39c8a23114b4dfaeb32db56bfd5b9fd7451b9feb8d4d38de625bc560b37ed8},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.36218. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models are increasingly evaluated in specialized domains such as law, medicine, software engineering, and cybersecurity, yet film remains comparatively underexplored despite requiring long-form narrative integration, multilingual interpretation, and culturally situated audience judgments. We introduce CineSubBench, a benchmark for evaluating long-context film understanding from multilingual movie subtitles. A subtitle track represents a film as thousands of short, temporally ordered utterances from which models must reconstruct characters, relationships, events, causal progression, and themes without explicit scene or event structure. CineSubBench contains 1,012 films with complete subtitle coverage in six languages, yielding 6,072 tracks and 8.13M timestamped subtitle entries. It provides a matched multi-task, multilingual, and multicultural (MultiX) evaluation setting: seven tasks span narrative reconstruction and abstraction, genre prediction, age suitability, country-specific motion-picture ratings across ten national classification systems, and subtitle-grounded language safety. Across nine LLMs, plot premises are recovered more reliably than event-complete synopses; cross-lingual consistency varies substantially across models and languages; national rating systems expose distinct calibration patterns; and strong profanity is far easier to ground than mild obscenity. CineSubBench establishes film as a long-context LLM evaluation domain and provides a unified benchmark for measuring narrative, multilingual, cultural, and evidence-grounding capabilities.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.AI).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Emerging Technologies (cs.ET); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.36218 — 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 2026-10-07T15:54:53.792Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).