Reinforcement learning recruits rather than creates a functional welfare axis in language models, as reward and punishment vectors from a maze task generalize to unrelated settings and appear in pretrain-only models.
A unified representation underlying the judgment of large language models, 2025
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Linear probes on residual-stream activations identify a shared preference vector in LLMs that tracks choices across prompts and causally steers decisions even for anti-correlated personas.
LLMs implement a second-order confidence architecture where the PANL activation encodes both error likelihood and the ability to correct it, beyond verbal confidence or log-probabilities.
citing papers explorer
-
How's it going? Reinforcement learning in language models recruits a functional welfare axis
Reinforcement learning recruits rather than creates a functional welfare axis in language models, as reward and punishment vectors from a maze task generalize to unrelated settings and appear in pretrain-only models.
-
Probing Persona-Dependent Preferences in Language Models
Linear probes on residual-stream activations identify a shared preference vector in LLMs that tracks choices across prompts and causally steers decisions even for anti-correlated personas.
-
How LLMs Detect and Correct Their Own Errors: The Role of Internal Confidence Signals
LLMs implement a second-order confidence architecture where the PANL activation encodes both error likelihood and the ability to correct it, beyond verbal confidence or log-probabilities.