# Know Thyself? On the Incapability and Implications of AI Self-Recognition

arXiv: https://arxiv.org/abs/2510.03399 · HTML: https://mlsanity.com/paper/2510.03399/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 31 references that are in the map.
- First posted on arXiv 3 Oct 2025.

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

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature](https://mlsanity.com/paper/2301.11305/) (2023)
- [LLM Evaluators Recognize and Favor Their Own Generations](https://mlsanity.com/paper/2404.13076/) (2024)
- [GLTR: Statistical Detection and Visualization of Generated Text](https://mlsanity.com/paper/1906.04043/) (2019)
- [Self-Preference Bias in LLM-as-a-Judge](https://mlsanity.com/paper/2410.21819/) (2024)
- [DetectLLM: Leveraging Log Rank Information for Zero-Shot Detection of Machine-Generated Text](https://mlsanity.com/paper/2306.05540/) (2023)
- [Large Language Models can Strategically Deceive their Users when Put Under Pressure](https://mlsanity.com/paper/2311.07590/) (2023)
- [Consciousness in Artificial Intelligence: Insights from the Science of Consciousness](https://mlsanity.com/paper/2308.08708/) (2023)
- [Deception Abilities Emerged in Large Language Models](https://mlsanity.com/paper/2307.16513/) (2023)
- [Have Large Language Models Developed a Personality?: Applicability of Self-Assessment Tests in Measuring Personality in LLMs](https://mlsanity.com/paper/2305.14693/) (2023)
- [Does It Make Sense to Speak of Introspection in Large Language Models?](https://mlsanity.com/paper/2506.05068/) (2025)
- [I Think, Therefore I am: Benchmarking Awareness of Large Language Models Using AwareBench](https://mlsanity.com/paper/2401.17882/) (2024)
- [Inspection and Control of Self-Generated-Text Recognition Ability in Llama3-8b-Instruct](https://mlsanity.com/paper/2410.02064/) (2024)
- [Self-Cognition in Large Language Models: An Exploratory Study](https://mlsanity.com/paper/2407.01505/) (2024)
- [Robot self/other distinction: active inference meets neural networks learning in a mirror](https://mlsanity.com/paper/2004.05473/) (2020)
- [AI Awareness](https://mlsanity.com/paper/2504.20084/) (2025)
- [I'm Spartacus, No, I'm Spartacus: Measuring and Understanding LLM Identity Confusion](https://mlsanity.com/paper/2411.10683/) (2024)

## Built on by (most cited first, 8 of 8)

- [Moral Susceptibility and Robustness under Persona Role-Play in Large Language Models](https://mlsanity.com/paper/2511.08565/) (2025)
- [Self-Recognition Finetuning can Prevent and Reverse Emergent Misalignment](https://mlsanity.com/paper/2606.23700/) (2026)
- [Self-Generated Text Recognition: Quality Heuristics, Cross-Task Transfer, and Downstream Bias in LLM Evaluation](https://mlsanity.com/paper/2608.26159/) (2026)
- [Strangers to Themselves: What Language Models Say About Themselves Is Generic](https://mlsanity.com/paper/2609.09899/) (2026)
- [Style, Not Self: Surface Cues Explain Zero-Shot Code Attribution by Large Language Models](https://mlsanity.com/paper/2609.30048/) (2026)
- [Using LLMs to Detect LLM-Generated Texts: A Cross-Generation Analysis](https://mlsanity.com/paper/2609.34691/) (2026)
- [A Shared Taste for Model-Written Text: The Generator-by-Selector Matrices of "AI-AI Bias" Show No Detectable Own-Model Premium](https://mlsanity.com/paper/2610.00369/) (2026)
- [Cross-Model In-Context Neurofeedback Reveals (Limited) Activation Control in LLMs](https://mlsanity.com/paper/2610.20179/) (2026)

## Abstract (arXiv)

Self-recognition is a crucial metacognitive capability for AI systems, relevant not only for psychological analysis but also for safety, particularly in evaluative scenarios. Motivated by contradictory interpretations of whether models possess self-recognition (Panickssery et al., 2024; Davidson et al., 2024), we introduce a systematic evaluation framework that can be easily applied and updated. Specifically, we measure how well 10 contemporary larger language models (LLMs) can identify their own generated text versus text from other models through two tasks: binary self-recognition and exact model prediction. Different from prior claims, our results reveal a consistent failure in self-recognition. Only 4 out of 10 models predict themselves as generators, and the performance is rarely above random chance. Additionally, models exhibit a strong bias toward predicting GPT and Claude families. We also provide the first evaluation of model awareness of their own and others' existence, as well as the reasoning behind their choices in self-recognition. We find that the model demonstrates some knowledge of its own existence and other models, but their reasoning reveals a hierarchical bias. They appear to assume that GPT, Claude, and occasionally Gemini are the top-tier models, often associating high-quality text with them. We conclude by discussing the implications of our findings on AI safety and future directions to develop appropriate AI self-awareness.