Abstract
Large Reasoning Models (LRMs) produce long, explicit chains of intermediate steps before generating a final answer at inference time. These intermediate traces dominate latency, memory usage, and serving cost, even though the final answer correctness is not causally related to the trace correctness and the trace length is not a reliable indicator of the problem complexity. This raises a natural question: can the computation expressed in these intermediate tokens be internalized into the parameters of a language model, enabling it to produce answers directly (or with much shorter intermediate traces)?
We introduce masked distillation, a knowledge-distillation framework in which a student LLM is trained to predict only the solution tokens conditioned on the question, while a reasoning teacher provides feedback on the student's responses after conditioning on the question and its own CoT trace.
We instantiate this framework in two settings: (i) a self-distillation setting, in which the same model serves as the teacher in thinking mode and as the student in non-thinking mode, and (ii) a dual-model setting, in which a larger reasoning teacher supervises a separate smaller non-thinking student over the solution tokens.
By treating intermediate tokens as a scaffold which reasoning models use to fit over the solution tokens, we additionally vary the length of intermediate-token scaffolding the student is supervised on, interpolating between full internalization (the student emits only the solution) and no internalization (the student emits the full trace before the answer). We evaluate the framework through controlled experiments on two reasoning domains: GSM8K (grade-school arithmetic) and Countdown (a number-puzzle search task).
Blogger's Review: This research offers an innovative approach to internalizing reasoning in language models, significantly reducing resource consumption during reasoning processes and showcasing the immense potential of knowledge distillation in enhancing model efficiency.