@InProceedings{xu:2026:wmt,
  author    = {Xu, Jia},
  title     = {SpinPop: A Fast Spin Metric for the WMT26 Metrics Shared Task},
  booktitle      = {Proceedings of the Eleventh Conference on Machine Translation},
  month          = {October},
  year           = {2026},
  address        = {Budapest, Hungary},
  publisher      = {Association for Computational Linguistics},
  pages     = {1764--1769},
  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 results 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.},
  url       = {https://aclanthology.org/2026.wmt-1.110}
}