multilingual-reasoning

Tag

Cards List
#multilingual-reasoning

Enhancing Multilingual Reasoning via Steerable Model Merging

arXiv cs.CL · 2026-06-18 Cached

This paper proposes ST-Merge, a steerable model merging framework that uses a gated cross-attention mechanism to adaptively modulate contributions of a multilingual model and a reasoning model, outperforming fixed merging approaches on multilingual reasoning benchmarks across 21 languages.

0 favorites 0 likes
#multilingual-reasoning

Rethinking the Multilingual Reasoning Gap with Layer Swap

arXiv cs.CL · 2026-05-27 Cached

This paper revisits the multilingual reasoning gap in LLMs, finding it smaller than previously reported under comparable supervision. It introduces Layer Swap, which transfers mid-layer weights from an English reasoning specialist to native language specialists, nearly closing the gap while preserving native-language chain-of-thought.

0 favorites 0 likes
#multilingual-reasoning

x1: Learning to Think Adaptively Across Languages and Cultures

arXiv cs.CL · 2026-04-21 Cached

Researchers introduce x1, a family of reasoning models that adaptively select optimal languages for reasoning on a per-instance basis, demonstrating that language choice impacts reasoning quality in multilingual and cultural tasks.

0 favorites 0 likes
#multilingual-reasoning

Large Reasoning Models Are (Not Yet) Multilingual Latent Reasoners

arXiv cs.CL · 2026-04-20 Cached

This paper investigates multilingual latent reasoning in large reasoning models across 11 languages, revealing that while latent reasoning capabilities exist, they are unevenly distributed—stronger in resource-rich languages and weaker in low-resource ones. The study finds that despite surface-level differences, the internal reasoning mechanisms are largely aligned with an English-centered pathway.

0 favorites 0 likes
← Back to home

Submit Feedback