NeurIPS paper finds LLMs have brain-like "value" and "dopamine" neurons encoding reward

james_y_zou · x · 2026-11-17

A NeurIPS 2026 paper asks whether LLMs have a reward system. Prior work fit black-box probes on full hidden states, saying little about how reward info is organized; this work finds reward signals live in sparse neuron subsets:

The authors draw an analogy between these sparse subsets and OFC/VTA/SNc value and dopamine neurons in the brain.

Original post →

More from Research

Research channel →