# Pterodactyl: Pushing the Limits of Efficient Automated Translation Evaluation

**Authors:** Evelyn Y. Garland, Carola F. Berger  
**Published:** 10 Nov 2026  
**Links:** [arXiv](https://arxiv.org/abs/2611.14480) · [PDF](https://arxiv.org/pdf/2611.14480) · [This page](https://omen-bit.github.io/ai-paper-daily/paper/2611.14480.html)

## 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.

---

Notes written by AI from the paper, numbers copied from the abstract. Check the paper before you rely on them. From AI Papers Daily.