Re-examination of two LLM introspection paradigms with new controls shows models lack privileged access to internal states, performing equivalently with input-only classifiers or near chance on relabeled tasks.
arXiv preprint arXiv:2508.14802 , year =
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
representative citing papers
LLMs need metacognition to align expressed uncertainty with their actual knowledge boundaries, moving beyond knowledge expansion to reduce confident errors.
Proposes a two-gradient-field model with candidate order parameters alpha_dagger and kappa_c to unify phase transitions across learning theory and non-equilibrium chemistry.
Activation verbalization methods for LLMs largely reflect the verbalizer model's parametric knowledge rather than privileged information from the target model's activations.
citing papers explorer
-
Can LLMs Introspect? A Reality Check
Re-examination of two LLM introspection paradigms with new controls shows models lack privileged access to internal states, performing equivalently with input-only classifiers or near chance on relabeled tasks.
-
Hallucinations Undermine Trust; Metacognition is a Way Forward
LLMs need metacognition to align expressed uncertainty with their actual knowledge boundaries, moving beyond knowledge expansion to reduce confident errors.
-
Phase Transitions in Driven Informational Systems: A Two-Field Perspective on Learning Theory and Non-Equilibrium Chemistry
Proposes a two-gradient-field model with candidate order parameters alpha_dagger and kappa_c to unify phase transitions across learning theory and non-equilibrium chemistry.
-
Do Activation Verbalization Methods Convey Privileged Information?
Activation verbalization methods for LLMs largely reflect the verbalizer model's parametric knowledge rather than privileged information from the target model's activations.
- When to Call an Apple Red: Humans Follow Introspective Rules, VLMs Don't