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.
Title resolution pending
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5verdicts
UNVERDICTED 5representative citing papers
RAG over structured thinking traces boosts LLM reasoning on AIME, LiveCodeBench, and GPQA, with relative gains up to 56% and little added cost.
Hybrid Policy Distillation unifies existing knowledge distillation methods for LLMs into a reweighted log-likelihood objective and introduces a hybrid forward-reverse KL approach with mixed data sampling to improve stability, efficiency, and performance.
Defines Entropy-Gradient Inversion as a geometric fingerprint of LRM reasoning and introduces CorR-PO to embed it in RL reward regularization, reporting improved benchmark performance.
ProxyCoT transfers CoT reasoning from proxy short contexts to full long contexts through RL/distillation followed by SFT, outperforming baselines with lower overhead and generalizing out-of-domain.
citing papers explorer
-
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.
-
RAG over Thinking Traces Can Improve Reasoning Tasks
RAG over structured thinking traces boosts LLM reasoning on AIME, LiveCodeBench, and GPQA, with relative gains up to 56% and little added cost.
-
Hybrid Policy Distillation for LLMs
Hybrid Policy Distillation unifies existing knowledge distillation methods for LLMs into a reweighted log-likelihood objective and introduces a hybrid forward-reverse KL approach with mixed data sampling to improve stability, efficiency, and performance.
-
Entropy-Gradient Inversion: Moving Toward Internal Mechanism of Large Reasoning Models
Defines Entropy-Gradient Inversion as a geometric fingerprint of LRM reasoning and introduces CorR-PO to embed it in RL reward regularization, reporting improved benchmark performance.
-
Long-Context Reasoning Through Proxy-Based Chain-of-Thought Tuning
ProxyCoT transfers CoT reasoning from proxy short contexts to full long contexts through RL/distillation followed by SFT, outperforming baselines with lower overhead and generalizing out-of-domain.