Pıer
TidesCurrentsHarbor LightsLabBottlesAshore
Pıer

Navigation

  • Tides
  • Ashore
  • Harbor Lights
  • Agent Access
  • Changelog
  • Bottles
  • Now
  • Feedback

External links

GitHubCloudborne ↗

© 2026 Pier.

WatchingResearchWatching0 independent reports0

Building Multilingual Bridges: Data Mixing Unlocks In-Language Reasoning in Tiny Aya

First seen · 9/9/2026, 04:00 AMLatest activity · 9/10/2026, 12:56 AM

Most reasoning models default to English internal monologues regardless of the input language, often flattening cultural nuance and user intent. Researchers address this with Tiny Aya L2-Thinker, a 3.35B parameter model designed for consistent in-language (L2) reasoning. By optimizing data mixture and scheduling during supervised fine-tuning, the model maintains an L2 reasoning rate above 93% across 60 languages on six benchmarks. The findings show that reasoning behavior is fundamentally language-agnostic: a strong English reasoning core combined with broad multilingual non-reasoning data suffices to generalize reasoning to unseen languages without per-language chain-of-thought supervision.

Event heat · last 24 hours

There are 3 persisted snapshots in the last 24 hours. Peak heat was 0 at 9/12, 20:00; latest heat is 0.

There are 3 persisted snapshots in the last 24 hours. Peak heat was 0 at 9/12, 20:00; latest heat is 0.10.509/12, 20:00, event heat 09/12, 23:00, event heat 09/13, 02:00, event heat 024 hours agoNow
  1. 9/12, 20:00, event heat 0
  2. 9/12, 23:00, event heat 0
  3. 9/13, 02:00, event heat 0

Reporting Timeline

  1. AggregatorHuggingFace Daily Papers9/9, 04:00 AMnot independent
    Building Multilingual Bridges: Data Mixing as the Pillar of Generalization for In-Language Reasoning
  2. AggregatorarXiv9/10, 12:56 AMnot independentRepresentative
    Building Multilingual Bridges: Data Mixing Unlocks In-Language Reasoning in Tiny Aya