AI TrackerFrontier desk · AEST
Back to news
normalaitech

Label-Wording Augmentation in a Typed-Decision Encoder: Gains on Unfamiliar Words, Not on Abbreviations or Codes

arXiv cs.AI · 6 Nov 2026, 04:31 AEST

A study on a multilingual cross-encoder shows that label-wording augmentation improves accuracy for unfamiliar words but not for abbreviations or codes. The augmented model outperformed the previous version in various settings, achieving gains of up to 0.24 in accuracy.

Key facts

Read aloud

A study on a multilingual cross-encoder shows that label-wording augmentation improves accuracy for unfamiliar words but not for abbreviations or codes. The augmented model outperformed the previous version in various settings, achieving gains of up to zero point two four in accuracy. Typed-decision models score options that the caller supplies at request time, so their accuracy depends on label wording that the model's developer does not control. We compare two releases of a 307M-parameter multilingual cross-encoder, Ru-Jev, trained on thirteen Russian-language tasks; the later release adds an augmentation that presents labels in several surface forms. On held-out vocabularies made of ordinary or borrowed words English-derived jargon, office slang, department names, the augmented release is more accurate in every setting, by up to zero point two four. On abbreviations and opaque codes it gives no usable gain: on abbreviations it is not better, and worse on the clean slice, and on opaque codes both releases stay at or below chance once labels related to training options are removed.

Sources in this cluster