paper
arXiv cs.CL
November 11th, 2026 at 5:00 AM

Pterodactyl: Pushing the Limits of Efficient Automated Translation Evaluation

arXiv:2611.14480v1 Announce Type: new Abstract: 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.

#llm
#research

Get stories like this every Monday

The week's most important AI news in one email. Free, unsubscribe anytime.

Score: 3.15

Engagement proxy: 0

Canonical link: https://arxiv.org/abs/2611.14480