← 研踪 PaperTrailarXiv:2611.14480 · v1
Pterodactyl: Pushing the Limits of Efficient Automated Translation Evaluation
首次提交 2026-11-11 02:41
版本更新 2026-11-11 02:41
雷达观测 2026-11-11 13:07
摘要
In this paper, we present 1020 Group's submission to the WMT26 shared task on automated quality evaluation. Our system, Pterodactyl, was engineered specifically for subtasks 2 and 3, that is, segment-level quality score prediction and the detection of error-free segments. Pterodactyl is a highly customizable, ultra-low cost system optimized for binary classification in translation triage and data curation. It is based on an LLM-as-a-judge approach, with prompt engineering and model selection guided by ROC analysis. We also developed several variants of Pterodactyl that were specifically adapted for subtasks 3.
作者备注：6 pages, 4 figures
期刊信息：Proceedings of the Eleventh Conference on Machine Translation (WMT 2026), pp. 1638-1643, 2026
观测到的版本
相邻记录可能跳过中间版本；首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-11 02:41 · 最新观测版本
Pterodactyl: Pushing the Limits of Efficient Automated Translation Evaluation
In this paper, we present 1020 Group's submission to the WMT26 shared task on automated quality evaluation. Our system, Pterodactyl, was engineered specifically for subtasks 2 and 3, that is, segment-level quality score prediction and the detection of error-free segments. Pterodactyl is a highly customizable, ultra-low cost system optimized for binary classification in translation triage and data curation. It is based on an LLM-as-a-judge approach, with prompt engineering and model selection guided by ROC analysis. We also developed several variants of Pterodactyl that were specifically adapted for subtasks 3.
查看此版本解读 →查看此版本原文 ↗