Metraipolis › archive › dc_4567c8ff5b62

Wisdom in Unity: The Role of Multilingual Training in Figurative Language Identification in Proverbs — arXiv:2608.08090

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.08090
License (as archived)
CC0-1.0
Archived
2026-10-19T08:49:53.497Z
SHA-256 of the archived text
84aa50f475e820e4feaf073731073cfd279e7d4feec2f33e68dd548ac9bcffe0
Stable URL of this page
https://metraipolis.com/documento/dc_4567c8ff5b62

How to cite

Wisdom in Unity: The Role of Multilingual Training in Figurative Language Identification in Proverbs — arXiv:2608.08090 — arXiv (en), https://arxiv.org/abs/2608.08090 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4567c8ff5b62 (Metraipolis archive dc_4567c8ff5b62, sha256 84aa50f475e820e4feaf073731073cfd279e7d4feec2f33e68dd548ac9bcffe0)
BibTeX
@misc{dc4567c8ff5b62,
  title = {Wisdom in Unity: The Role of Multilingual Training in Figurative Language Identification in Proverbs — arXiv:2608.08090},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.08090},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4567c8ff5b62; sha256 84aa50f475e820e4feaf073731073cfd279e7d4feec2f33e68dd548ac9bcffe0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.08090. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Although multilingual approaches to figurative language identification are not new, the shift beyond language-homogeneous training data requires a clearer understanding of the contribution of translated multilingual supervision. We examine this question using 742 proverb concepts across 6,787 translated instances for seven languages. We evaluate five models including multilingual encoders and instruction-tuned LLMs through progressively increasing levels of multilingual supervision. Moreover, we introduce multidimensional annotation framework for proverbs that characterizes proverbs through four complementary figurative forms: Metaphorical, Moral/Advisory, Cause-Effect, and Culture-Specific. Our findings show that overall, adding multilingual training data beyond 50% provides only limited additional improvement, although the best supervision level varies across models and languages. Also, we show that combining diverse figurative forms yields the strongest overall performance. A notable finding is that the least frequent figurative form culture-specific exhibits the largest performance gains under multilingual supervision. Furthermore, the moral/advisory and culture-specific forms of proverb contribute more to instruct tuning LLM overall figurative identification performance. These findings motivate multilingual figurative identification to move beyond metaphor-centric taxonomies toward concept-level multidimensional frameworks that explicitly model complementary forms of figurative meanings that are context representative.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-11 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.08090 — 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 2026-10-19T08:49:41.846Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).