LLM hidden states contain a sparse reward subsystem consisting of value neurons that predict state value and dopamine neurons that encode step-level temporal difference errors.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Sparse Reward Subsystem in Large Language Models
LLM hidden states contain a sparse reward subsystem consisting of value neurons that predict state value and dopamine neurons that encode step-level temporal difference errors.