LLMs can learn (some) multi-step reasoning on filler tokens
by Wuschel Schulz and tvb
Research update of a project done as part of MARS 5 and the Meridian Visiting Researcher Programme. Filler-token reasoning is the ability to use extra tokens (such as a chain of thought) to reason about a task without using the words emitted at those token positions. This is possible because...
Nov 119