AdaMCoT uses dynamic routing of chain-of-thought reasoning in intermediary languages with a reward-based selector to improve cross-lingual factual consistency in LLMs.
哪些国家的工作时间比墨西哥人更长? (Which countries have longer working hours than Mexico?)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
AdaMCoT: Rethinking Cross-Lingual Factual Reasoning through Adaptive Multilingual Chain-of-Thought
AdaMCoT uses dynamic routing of chain-of-thought reasoning in intermediary languages with a reward-based selector to improve cross-lingual factual consistency in LLMs.