Preprint
Jul 2026
How Much is Left? LLMs Linearly Encode Their Remaining Output Length
Training minimal-capacity linear probes on frozen hidden states of three open-weight 7-8B models across seven completion-style datasets finds three converging pieces of evidence that LLMs maintain a plan-like internal representation of output length, interpreted as evidence that LLMs maintain a plan-like internal repre...
Mohamed Amine Merzouk, Dmitri Carpov, Mirko Bronzi et al.
· 1 citation