Metraipolis › archive › dc_bf5c05adb686

Retrieval-Enhanced Cultural Evaluation for Social Media Translation Training — arXiv:2611.02009

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.02009
License (as archived)
CC0-1.0
Archived
2026-11-03T11:10:40.555Z
SHA-256 of the archived text
7042659f67fb43ceb5d0ef6759f5372b89106bc249fdd4eb2032d2b615a91c06
Stable URL of this page
https://metraipolis.com/documento/dc_bf5c05adb686

How to cite

Retrieval-Enhanced Cultural Evaluation for Social Media Translation Training — arXiv:2611.02009 — arXiv (en), https://arxiv.org/abs/2611.02009 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bf5c05adb686 (Metraipolis archive dc_bf5c05adb686, sha256 7042659f67fb43ceb5d0ef6759f5372b89106bc249fdd4eb2032d2b615a91c06)
BibTeX
@misc{dcbf5c05adb686,
  title = {Retrieval-Enhanced Cultural Evaluation for Social Media Translation Training — arXiv:2611.02009},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.02009},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bf5c05adb686; sha256 7042659f67fb43ceb5d0ef6759f5372b89106bc249fdd4eb2032d2b615a91c06},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02009. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Social media translation requires preserving meaning while capturing the cultural nuances of user-generated content (UGC). However, gaps in the cultural knowledge of LLM-based evaluators can lead to inaccurate assessments and unreliable training rewards. To improve these signals, we use retrieval-enhanced cultural evaluation to train CUE-MT, a family of social media translation models. A calibrated, domain-specific Judger guides supervised data refinement and is augmented by an Agent for hard-example mining and reinforcement learning. The Agent retrieves relevant external evidence as needed and distills it into concise hints that the Judger uses to score translations and assign rewards. Across 9B, 27B, and 35B-A3B backbones, CUE-MT outperforms the evaluated open-source baselines of comparable size on CUE-MT-Bench and three public benchmarks. Human evaluation on CUE-MT-Bench shows cultural effectiveness gains of 7.44-15.12 percentage points over the strongest external baseline in each size group. Retrieval improves the Judger's four-way classification accuracy by 8.07 percentage points over a matched no-retrieval baseline that uses LLM-generated hints alone. Training ablations further support the combination of hard-example mining and Agent-enhanced rewards.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2611.02009 — 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 2026-11-03T10:59:52.320Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).