LLM chain-of-thought crosses a commitment boundary early; subsequent steps are epiphenomenal, enabling early-exit that shortens traces 55% with negligible performance change.
D eep T rans: Deep Reasoning Translation via Reinforcement Learning
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
RL with chrF reward trains LLMs to better utilize in-context linguistic knowledge for zero-shot translation of unseen languages, outperforming ICL and SFT.
SEMJ is a self-evolving multilingual LLM judge that turns cross-lingual inconsistency into iterative self-reflection, outperforming voting and reflection baselines on accuracy and consistency.
citing papers explorer
-
Beyond the Commitment Boundary: Probing Epiphenomenal Chain-of-Thought in Large Reasoning Models
LLM chain-of-thought crosses a commitment boundary early; subsequent steps are epiphenomenal, enabling early-exit that shortens traces 55% with negligible performance change.
-
Reinforcement Learning Elicits Contextual Learning of Unseen Language Translation
RL with chrF reward trains LLMs to better utilize in-context linguistic knowledge for zero-shot translation of unseen languages, outperforming ICL and SFT.
-
When Languages Disagree: Self-Evolving Multilingual LLM Judges
SEMJ is a self-evolving multilingual LLM judge that turns cross-lingual inconsistency into iterative self-reflection, outperforming voting and reflection baselines on accuracy and consistency.