# Emergent Introspection in AI is Content-Agnostic

arXiv: https://arxiv.org/abs/2603.05414 · HTML: https://mlsanity.com/paper/2603.05414/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 25 references that are in the map.
- First posted on arXiv 5 Mar 2026.

## Builds on (most cited first, 12 of 12)

- [Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs](https://mlsanity.com/paper/2502.17424/) (2025)
- [Looking Inward: Language Models Can Learn About Themselves by Introspection](https://mlsanity.com/paper/2410.13787/) (2024)
- [Tell me about yourself: LLMs are aware of their learned behaviors](https://mlsanity.com/paper/2501.11120/) (2025)
- [Emergent Introspective Awareness in Large Language Models](https://mlsanity.com/paper/2601.01828/) (2026)
- [Could a Large Language Model be Conscious?](https://mlsanity.com/paper/2303.07103/) (2023)
- [Language Models Fail to Introspect About Their Knowledge of Language](https://mlsanity.com/paper/2503.07513/) (2025)
- [Training Language Models to Explain Their Own Computations](https://mlsanity.com/paper/2511.08579/) (2025)
- [Self-Interpretability: LLMs Can Describe Complex Internal Processes that Drive Their Decisions](https://mlsanity.com/paper/2505.17120/) (2025)
- [Does It Make Sense to Speak of Introspection in Large Language Models?](https://mlsanity.com/paper/2506.05068/) (2025)
- [Privileged Self-Access Matters for Introspection in AI](https://mlsanity.com/paper/2508.14802/) (2025)
- [Latent Introspection: Models Can Detect Prior Concept Injections](https://mlsanity.com/paper/2602.20031/) (2026)
- [Steering Awareness: Detecting Activation Steering from Within](https://mlsanity.com/paper/2511.21399/) (2025)

## Built on by (most cited first, 7 of 7)

- [Prefill Awareness in Large Language Models](https://mlsanity.com/paper/2606.12747/) (2026)
- [Introspective Coupling: Self-Explanation Training Tracks Behavioral Change Despite Fixed Supervision](https://mlsanity.com/paper/2606.32038/) (2026)
- [Instrument Effects in Language-Model Honesty Evaluation: An Auditable Single-System Demonstration](https://mlsanity.com/paper/2607.14399/) (2026)
- [Measuring Activation Control in Large Language Models](https://mlsanity.com/paper/2608.21664/) (2026)
- [Phase Transitions in Driven Informational Systems: A Two-Field Perspective on Learning Theory and Non-Equilibrium Chemistry](https://mlsanity.com/paper/2605.16325/) (2026)
- [Open-Weight Masked Introspection: Measuring What Language Models Can Report About Their Own Computation](https://mlsanity.com/paper/2608.20569/) (2026)
- [A Sense of Proprioception in Language Models](https://mlsanity.com/paper/2610.17495/) (2026)

## Abstract (arXiv)

Introspection is a foundational cognitive ability, but its mechanism is not well understood. Recent work has shown that AI models can introspect. We study the mechanism of this introspection. We first extensively replicate Lindsey (2025)'s thought injection detection paradigm in large open-source models. We show that introspection in these models is content-agnostic: models can detect that an anomaly occurred even when they cannot reliably identify its content. The models confabulate injected concepts that are high-frequency and concrete (e.g., "apple"). They also require fewer tokens to detect an injection than to guess the correct concept (with wrong guesses coming earlier). We argue that a content-agnostic introspective mechanism is consistent with leading theories in philosophy and psychology.