SOLAR aligns soft-token probability mixtures across languages in embedding space during SFT and raises multilingual reasoning accuracy by up to 17.7 points over the base model.
Crosslingual Reasoning through Test-Time Scaling
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
fields
cs.CL 5verdicts
UNVERDICTED 5representative citing papers
LANG combines language-adaptive hint guidance, progressive decay, and difficulty-tailored learning horizons in RL to boost non-English reasoning performance while preserving language consistency.
Four of five tested LLMs showed better diagnostic reasoning and accuracy when prompted in English than in French on physician-scored clinical vignettes.
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.
The paper introduces Language Specific Knowledge (LSK) and shows that selecting an optimal non-English language for a query can improve LLM performance on cultural and social norm datasets.
citing papers explorer
-
Soft Token Alignment for Cross-Lingual Reasoning
SOLAR aligns soft-token probability mixtures across languages in embedding space during SFT and raises multilingual reasoning accuracy by up to 17.7 points over the base model.
-
LANG: Reinforcement Learning for Multilingual Reasoning with Language-Adaptive Hint Guidance
LANG combines language-adaptive hint guidance, progressive decay, and difficulty-tailored learning horizons in RL to boost non-English reasoning performance while preserving language consistency.
-
Prompting language influences diagnostic reasoning and accuracy of large language models
Four of five tested LLMs showed better diagnostic reasoning and accuracy when prompted in English than in French on physician-scored clinical vignettes.
-
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.
-
Language Specific Knowledge: Do Models Know Better in X than in English?
The paper introduces Language Specific Knowledge (LSK) and shows that selecting an optimal non-English language for a query can improve LLM performance on cultural and social norm datasets.