ST-Merge uses gated cross-attention to adaptively weight source models during merging, outperforming baselines on multilingual reasoning tasks across 21 languages.
Question Translation Training for Better Multilingual Reasoning
5 Pith papers cite this work, alongside 5 external citations. Polarity classification is still indexing.
5
Pith papers citing it
5
external citations · OpenAlex
fields
cs.CL 5years
2026 5verdicts
UNVERDICTED 5representative citing papers
Luar is a reinforcement learning method enabling reasoning language models to decide when to invoke English translation for improved multilingual reasoning.
Unsupervised RL enforces cross-lingual self-consistency to improve multilingual math reasoning by up to 21.7% on MGSM without gold answers or parallel data, with generalization to unseen languages.
COPSD improves mathematical reasoning in low-resource languages by having LLMs self-distill from their own high-resource English behavior via token-level divergence on rollouts with privileged crosslingual context.
Treating language as a latent variable via polyGRPO RL improves Qwen2.5-7B-Instruct by 6.72% on English reasoning benchmarks and 6.89% on multilingual ones, with cross-task gains on commonsense reasoning from math-only training.
citing papers explorer
-
Enhancing Multilingual Reasoning via Steerable Model Merging
ST-Merge uses gated cross-attention to adaptively weight source models during merging, outperforming baselines on multilingual reasoning tasks across 21 languages.
-
Learning When to Translate for Multilingual Reasoning
Luar is a reinforcement learning method enabling reasoning language models to decide when to invoke English translation for improved multilingual reasoning.
-
Cross-lingual Self-Consistency for Multilingual Reasoning with Language Models
Unsupervised RL enforces cross-lingual self-consistency to improve multilingual math reasoning by up to 21.7% on MGSM without gold answers or parallel data, with generalization to unseen languages.
-
Crosslingual On-Policy Self-Distillation for Multilingual Reasoning
COPSD improves mathematical reasoning in low-resource languages by having LLMs self-distill from their own high-resource English behavior via token-level divergence on rollouts with privileged crosslingual context.
-
Language as a Latent Variable for Reasoning Optimization
Treating language as a latent variable via polyGRPO RL improves Qwen2.5-7B-Instruct by 6.72% on English reasoning benchmarks and 6.89% on multilingual ones, with cross-task gains on commonsense reasoning from math-only training.