Skip to content
Conference Open access

SpinPop: A Fast Spin Metric for the WMT26 Metrics Shared Task

2026 · Proceedings of the Eleventh Conference on Machine Translation · 0 citations · 18 references

Abstract

We describe our submission to the WMT26 Shared Task on Automated Translation Quality Evaluation. Our primary system is a per-language-pair, z -normalized, weight-free ensemble that combines six complementary signals: our novel metric SpinPop, COMET-22, and four large language model judges. SpinPop is training-free, constant-cost, tokenization-agnostic, broadly multilingual, and deterministic. Within its encoder’s language coverage it scores every segment, with or without a reference, using a single frozen-encoder pass that runs locally and requires no paid API calls. Our system achieves a mean per-language-pair Pearson correlation of 0 . 8534 , ranking second on the WMT26 Task 2 leaderboard. The re-sults demonstrate that a simple unsupervised ensemble of a spin-code metric, a neural metric, and multiple LLM judges can achieve top-tier performance with equal weights.

Read PDF

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.