States Hidden in Hidden States: Implicit Discrete State Representations Emerge in LLMs' Hidden States

Understand

Large Language Models (LLMs) exhibit emergent abilities that may reveal aspects of their internal mechanisms.

• We study one such capability: directly performing extended sequences of calculations without generating chain-of-thought solutions.
• The strongest models in our evaluation can directly output sums with up to 15 addends, where operands are sampled from 1 to 100.
• We hypothesize that models form Implicit Discrete State Representations (IDSRs) within their hidden states and use them for internal symbolic calculation.