Tal Linzen
Department of Linguistics and Center for Data Science, New York University
Critic Current evidence and current methods do not support the claims being made
Tal Linzen is Associate Professor of Linguistics and Data Science at New York University, where he directs the Computation and Psycholinguistics Lab, and a research scientist who has worked extensively on targeted diagnostic evaluations of neural network representations.
In Can LLMs Introspect? A Reality Check (arXiv:2605.26242, May 2026), co-authored with Shashwat Singh and Shauli Ravfogel, Linzen audited the two primary experimental paradigms used to claim that large language models possess introspective self-knowledge, namely activation intervention detection and hidden-state prediction. By introducing external input-only classifiers and relabeled control conditions that strip surface semantic correlations from the prompt, Singh, Linzen, and Ravfogel demonstrated that apparent introspective accuracy in standard evaluation setups often collapses to near-chance or can be matched by an observer with zero access to the model’s internal activations.
Linzen is classified as a Critic on this site. His work establishes strict methodological baselines that any claim of machine introspection or higher-order self-monitoring must clear before behavioral or steering-vector reports are treated as evidence of privileged internal access.
Known for. Can LLMs Introspect? A Reality Check, mechanistic evaluation of syntactic and metacognitive claims in language models
Coverage on this site
- LLM Introspection After the November 2026 Quanta Report, Concept Injection Against the Reality Check November 2026
Related researchers
- Jack LindseyAnthropic, Transformer CircuitsIntrospection circuits in language models, mind viruses in multi-agent systems, Global Workspace representations
- Shashwat SinghCenter for Data Science, New York UniversityCan LLMs Introspect? A Reality Check, concept erasure and causal representation auditing in language models
- Shauli RavfogelCenter for Data Science, New York University and Bar-Ilan UniversityCan LLMs Introspect? A Reality Check, linear concept erasure, causal probing of neural representations
- Scott AaronsonUniversity of Texas at Austin, Department of Computer ScienceQuantum complexity theory, mathematical counterexamples to Integrated Information Theory (Phi in expander graphs and Reed-Solomon grids), speaker at UT Austin Consciousness and Intelligence 2026
- Michel BitbolCNRSPhenomenology and quantum physics, the critique of objectivist reduction, first-person knowledge as irreducible, collaboration with Claire Petitmengin
- Ned BlockDepartment of Philosophy, New York UniversityDistinction between Phenomenal and Access Consciousness (1995), Blockhead argument against behavioral tests, The Border Between Seeing and Thinking (2023)
Tal Linzen is listed with the other critics and skeptics, who hold that current evidence and current methods do not support the claims being made. The positions themselves are set out in the index of consciousness theories. Every researcher covered on this site is indexed in the directory of consciousness researchers.