Resolve training-inference discrepancy in reverse reasoning
Resolve the training-inference discrepancy, or exposure bias, that remains unresolved in the Reverse Enhanced Thinking (REvThink) approach for training student models with bidirectional reasoning paths.
References
Finally, the training-inference discrepancy (exposure bias) remains an unresolved issue.
— Construting Reverse Thinking: Developing Large Language Models' Reverse Thingking Ability
(2609.24760 - Liu et al., 21 Sep 2026) in Section 1, subsection “Long Chain-of-Thought (Long CoT) reasoning,” paragraph on Feasible Reflection and subsequent discussion of REvThink