A new parallel reasoning dataset enables LLMs to shift reasoning to non-English languages via SFT and RLVR while matching or exceeding baseline performance.
Not All Languages Are Created Equal in LLMs: Improving Multilingual Capability by Cross-Lingual-Thought Prompting , booktitle =
9 Pith papers cite this work, alongside 55 external citations. Polarity classification is still indexing.
9
Pith papers citing it
55
external citations · OpenAlex
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
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.
SSU mitigates catastrophic forgetting in low-resource LLM target-language adaptation by scoring and column-wise freezing source-critical parameters, reducing source degradation to ~3% versus ~20% for full fine-tuning while matching target performance.
DIP interleaves English word translations into non-English prompts to boost multilingual reasoning on synthetic benchmarks spanning 10-200 languages.
Interpreting harmful Discord messages requires integrating external knowledge and extended context, not just local message-level classification; LLMs leverage local context better than humans but still fail on coded language and community-specific references.
A multilingual self-consistency plus self-critique method raises cultural alignment scores on English queries by 5.03% on the BLEnD benchmark using only self-generated data.
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 unifies perspectives on Long CoT in reasoning LLMs by introducing a taxonomy, detailing characteristics of deep reasoning and reflection, and discussing emergence phenomena and future directions.
Lius improves LLM translation for Kupang Malay by 4-13 points over baselines via continual instruction tuning with dictionary-derived instructions.
citing papers explorer
-
ReasonXL: Shifting LLM Reasoning Language Without Sacrificing Performance
A new parallel reasoning dataset enables LLMs to shift reasoning to non-English languages via SFT and RLVR while matching or exceeding baseline performance.
-
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.
-
Mitigating Catastrophic Forgetting in Target Language Adaptation of LLMs via Source-Shielded Updates
SSU mitigates catastrophic forgetting in low-resource LLM target-language adaptation by scoring and column-wise freezing source-critical parameters, reducing source degradation to ~3% versus ~20% for full fine-tuning while matching target performance.
-
Dictionary Insertion Prompting for Multilingual Reasoning on Multilingual Large Language Models
DIP interleaves English word translations into non-English prompts to boost multilingual reasoning on synthetic benchmarks spanning 10-200 languages.
-
Understanding Interpretation Difficulty in Harmful Online Communication: Insights from Cybercrime Communities
Interpreting harmful Discord messages requires integrating external knowledge and extended context, not just local message-level classification; LLMs leverage local context better than humans but still fail on coded language and community-specific references.
-
Cross-Lingual Consensus: Aligning Multilingual Cultural Knowledge via Multilingual Self-Consistency
A multilingual self-consistency plus self-critique method raises cultural alignment scores on English queries by 5.03% on the BLEnD benchmark using only self-generated data.
-
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.
-
Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models
The paper unifies perspectives on Long CoT in reasoning LLMs by introducing a taxonomy, detailing characteristics of deep reasoning and reflection, and discussing emergence phenomena and future directions.
-
Lius: Translation Model Based Instructional Lingustic Using Continual Instruction Tuning In Kupang Malay
Lius improves LLM translation for Kupang Malay by 4-13 points over baselines via continual instruction tuning with dictionary-derived instructions.