OPEN
laya-slotjudge-m46
laya-slotjudge-m46 chooses a proposed slot value or not specified across 46 training languages. See how real candidate lists change its results.
By Christophe Cruz, Hussam Ghanem and Hocine Cherifi · Model-card release: 4 Nov 2026
A multilingual Laya fine-tune that chooses a proposed value for a dialogue slot or answers not specified. It needs candidate values from another component and does not extract spans. The released seed was selected on development data from three training seeds; its card reports results for 46 training languages and five held-out languages.
Facts
- Size
- About 322M, according to the card
- Licence
- CC BY-SA 4.0 weights
- Inputs
- Dialogue message, context and candidate values; 1,024 input tokens and 48 per option
- Access
- Laya runtime; public model.safetensors, configuration and calibration files
Claims and sources
- On MTOP across six languages, the authors report slot F1 0.953 with oracle candidate lists and 0.488 with real proposers, whose candidate recall is 0.578. With real lists on MTOP and MASSIVE, ECE remains about 0.15 to 0.17. Thresholds and temperature need fitting to the user's own data. vendor reportedsource
- At the card's 1% target risk, the development-set threshold keeps 60% of correct fills with oracle lists but only 3% with real lists. These are development-set operating points, not guaranteed test error rates. vendor reportedsource
Links
Source: Model card and weights → Source: Code →
Related projects
No related projects are listed in the registry.