Metraipolis › archive › dc_07bed5087de7
EviSI: An Evidence-Based Evaluation Agent for Simultaneous Interpreting — arXiv:2609.08171
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.08171
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T12:48:42.787Z
- SHA-256 of the archived text
f6b070775bdd1becf0351c32d02d15f7b5f5ffb592c0d291c06526a0fdfafe03- Stable URL of this page
https://metraipolis.com/documento/dc_07bed5087de7
How to cite
EviSI: An Evidence-Based Evaluation Agent for Simultaneous Interpreting — arXiv:2609.08171 — arXiv (en), https://arxiv.org/abs/2609.08171 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_07bed5087de7 (Metraipolis archive dc_07bed5087de7, sha256 f6b070775bdd1becf0351c32d02d15f7b5f5ffb592c0d291c06526a0fdfafe03)
BibTeX
@misc{dc07bed5087de7,
title = {EviSI: An Evidence-Based Evaluation Agent for Simultaneous Interpreting — arXiv:2609.08171},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.08171},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_07bed5087de7; sha256 f6b070775bdd1becf0351c32d02d15f7b5f5ffb592c0d291c06526a0fdfafe03},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.08171. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Low-latency simultaneous speech-to-speech translation must keep pace with ongoing speech while preserving key information. To meet these demands, systems use segmentation, reformulation and condensation to reorganize and rephrase information. However, metrics developed for text translation, including BLEU and COMET, may not consistently distinguish faithful adaptations from semantic errors. We propose EviSI, a large language model evaluation agent combining Multidimensional Quality Metrics (MQM) with criteria developed with professional interpreters. Shared source evidence guides assessment across four dimensions: Anchor, Event, Logic and Fluency. Verified errors are deduplicated before deterministic scoring. On human-rated English to Chinese and Chinese to English data, EviSI recovers the aggregate English to Chinese human system ranking. Mean within-dataset Kendall correlations for system rankings reach 0.707 and 0.467, respectively, exceeding evaluated BLEU and COMET baselines. A multilingual extension to five directions without human ratings retains the dimensions and scoring rule, showing positive system ranking correlations with COMET throughout. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CL). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2609.08171 — 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 2026-10-16T12:30:25.166Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).