| title | PolyRoute: A Twelve-Language and Code-Mixed Benchmark for Typed-Decision Routing, with Baselines and a Leaderboard |
|---|---|
| authors | Mohammed Nayeem Khan, Sarun Kumar K S |
| date | 2026-11-10 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2611.13843 |
| upvotes | 2 (Hugging Face Daily Papers, 2026-11-14) |
| links | abs pdf hf |
| cite | |
| abstract | Typed-decision encoders answer a question about a text in one forward pass, but their behaviour outside English is rarely measured on a fixed yardstick. We release PolyRoute: 322 native-language support messages in 12 languages and 9 writing systems, 156 code-mixed or romanised messages (Hinglish, Spanglish, Arabizi), 967 optional native training rows, and a protocol for a three-way department-routing decision. Labels come from Qwen3.8-27B with a blind second pass (91% of candidates kept); an independent model, gemma4-31b, agrees on 97.2% of test items, and the largest character 5-gram similarity between any test text and any training text is 0.33. A leaderboard of 13 systems gives 61.2% for the English-root checkpoint, 77.3% for the shipped multilingual one and 96.6% for the best fine-tune; TF-IDF with logistic regression reaches 91.9%. On four withheld languages the three multilingual systems score 77%, 90% and 93%. On code-mixed text the English root (85%) is nominally ahead of the shipped multilingual checkpoint (79%; p=0.134). The split resolves differences only above about 4 points. All texts and labels are LLM-generated. |
bibtex
@misc{khan2026polyroute,
title={PolyRoute: A Twelve-Language and Code-Mixed Benchmark for Typed-Decision Routing, with Baselines and a Leaderboard},
author={Mohammed Nayeem Khan and Sarun Kumar K S},
year={2026},
eprint={2611.13843},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2611.13843}
}