# Reality Monitoring in Large Language Models: Self-Knowledge That Transforms with Conversation Memory

arXiv: https://arxiv.org/abs/2607.23927 · HTML: https://mlsanity.com/paper/2607.23927/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 77 references that are in the map.
- First posted on arXiv 27 Jul 2026.

## Builds on (most cited first, 19 of 19)

- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [Language Models (Mostly) Know What They Know](https://mlsanity.com/paper/2207.05221/) (2022)
- [Towards Automated Circuit Discovery for Mechanistic Interpretability](https://mlsanity.com/paper/2304.14997/) (2023)
- [Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task](https://mlsanity.com/paper/2210.13382/) (2022)
- [Large Language Models Sensitivity to The Order of Options in Multiple-Choice Questions](https://mlsanity.com/paper/2308.11483/) (2023)
- [Linearity of Relation Decoding in Transformer Language Models](https://mlsanity.com/paper/2308.09124/) (2023)
- [Large Language Models Often Know When They Are Being Evaluated](https://mlsanity.com/paper/2505.23836/) (2025)
- [Looking Inward: Language Models Can Learn About Themselves by Introspection](https://mlsanity.com/paper/2410.13787/) (2024)
- [How Do Large Language Models Acquire Factual Knowledge During Pretraining?](https://mlsanity.com/paper/2406.11813/) (2024)
- [Large Language Models Hallucination: A Comprehensive Survey](https://mlsanity.com/paper/2510.06265/) (2025)
- [Probing and Steering Evaluation Awareness of Language Models](https://mlsanity.com/paper/2507.01786/) (2025)
- [Does It Make Sense to Speak of Introspection in Large Language Models?](https://mlsanity.com/paper/2506.05068/) (2025)
- [Interpretability without actionability: mechanistic methods cannot correct language model errors despite near-perfect internal representations](https://mlsanity.com/paper/2603.18353/) (2026)
- [Because we have LLMs, we Can and Should Pursue Agentic Interpretability](https://mlsanity.com/paper/2506.12152/) (2025)
- [Evidence for Limited Metacognition in LLMs](https://mlsanity.com/paper/2509.21545/) (2025)
- [Assessing Episodic Memory in LLMs with Sequence Order Recall Tasks](https://mlsanity.com/paper/2410.08133/) (2024)
- [MIRROR: A Hierarchical Benchmark for Metacognitive Calibration in Large Language Models](https://mlsanity.com/paper/2604.19809/) (2026)
- [The Metacognitive Monitoring Battery: A Cross-Domain Benchmark for LLM Self-Monitoring](https://mlsanity.com/paper/2604.15702/) (2026)

## Abstract (arXiv)

A conversational AI that cannot tell its own output from what a user said will treat its own mistakes as user-provided facts. In humans, this capacity is called reality monitoring, and its failures are linked to hallucinations, delusions, and confabulation, yet whether LLMs possess it remains untested. Here we show, across two experiments and six LLMs, that source attribution depends on how conversational memory is structured: ceiling accuracy for self-generated content under minimal memory demands reverses to a fragile external-item advantage once episodic delay removes that shortcut. Feedback exposes two failures: in some models, internal and external judgments swap; in others, accuracy improves while confidence decouples from correctness, dissociations invisible to existing benchmarks. Across models, this pattern implicates active, not aggregate, parameter count. This suggests that as AI systems take on autonomous, multi-turn roles, evaluating what they know is not enough: tracking where that knowledge came from may matter equally.