# Self-Recognition in Language Models

arXiv: https://arxiv.org/abs/2407.06946 · HTML: https://mlsanity.com/paper/2407.06946/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 45 references that are in the map.
- First posted on arXiv 9 Jul 2024.

## Builds on (most cited first, 23 of 23)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021)
- [LLM Evaluators Recognize and Favor Their Own Generations](https://mlsanity.com/paper/2404.13076/) (2024)
- [Large Language Models Can Self-Improve](https://mlsanity.com/paper/2210.11610/) (2022)
- [Large Language Models Are Not Robust Multiple Choice Selectors](https://mlsanity.com/paper/2309.03882/) (2023)
- [MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers](https://mlsanity.com/paper/2102.01454/) (2021)
- [Provable Robust Watermarking for AI-Generated Text](https://mlsanity.com/paper/2306.17439/) (2023)
- [Mindstorms in Natural Language-Based Societies of Mind](https://mlsanity.com/paper/2305.17066/) (2023)
- [Watermark Stealing in Large Language Models](https://mlsanity.com/paper/2402.19361/) (2024)
- [LLMs as Narcissistic Evaluators: When Ego Inflates Evaluation Scores](https://mlsanity.com/paper/2311.09766/) (2023)
- [When Should We Prefer Offline Reinforcement Learning Over Behavioral Cloning?](https://mlsanity.com/paper/2204.05618/) (2022)
- [Mitigating Label Biases for In-context Learning](https://mlsanity.com/paper/2305.19148/) (2023)
- [Evaluating Language Model Agency through Negotiations](https://mlsanity.com/paper/2401.04536/) (2024)
- [Unsupervised Pretraining for Sequence to Sequence Learning](https://mlsanity.com/paper/1611.02683/) (2016)
- [The Ethical Need for Watermarks in Machine-Generated Language](https://mlsanity.com/paper/2209.03118/) (2022)
- [Beyond Performance: Quantifying and Mitigating Label Bias in LLMs](https://mlsanity.com/paper/2405.02743/) (2024)
- [Unsupervised Contrast-Consistent Ranking with Language Models](https://mlsanity.com/paper/2309.06991/) (2023)

## Built on by (most cited first, 18 of 18)

- [Does It Make Sense to Speak of Introspection in Large Language Models?](https://mlsanity.com/paper/2506.05068/) (2025)
- [Localized Cultural Knowledge is Conserved and Controllable in Large Language Models](https://mlsanity.com/paper/2504.10191/) (2025)
- [Large language models for artificial general intelligence (AGI): A survey of foundational principles and approaches](https://mlsanity.com/paper/2501.03151/) (2025)
- [AI Awareness](https://mlsanity.com/paper/2504.20084/) (2025)
- [Inflated Excellence or True Performance? Rethinking Medical Diagnostic Benchmarks with Dynamic Evaluation](https://mlsanity.com/paper/2510.09275/) (2025)
- [Reasoning-Driven Synthetic Data Generation and Evaluation](https://mlsanity.com/paper/2603.29791/) (2026)
- [CIAware-Bench: Benchmarking Control Intervention Awareness Across Frontier LLMs](https://mlsanity.com/paper/2606.11063/) (2026)
- [What Are They Filtering Out? An Experimental Benchmark of Filtering Strategies for Harm Reduction in Pretraining Datasets](https://mlsanity.com/paper/2503.05721/) (2025)
- [Mirage of Mastery: Memorization Tricks LLMs into Artificially Inflated Self-Knowledge](https://mlsanity.com/paper/2506.18998/) (2025)
- [The Epistemic Asymmetry of Consciousness Self-Reports: A Formal Analysis of AI Consciousness Denial](https://mlsanity.com/paper/2501.05454/) (2024)
- [The Future of Facts: Tracing the Factual Generation-Verification Gap](https://mlsanity.com/paper/2605.27564/) (2026)
- [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)
- [The Assistant as a Privileged Persona: A canonical reference in cross-persona self-recognition](https://mlsanity.com/paper/2606.00545/) (2026)
- [The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes](https://mlsanity.com/paper/2606.11470/) (2026)
- [Asymmetric Communication: Large Language Models and Language Games](https://mlsanity.com/paper/2607.28137/) (2026)
- [AwarenessBench: Assessing Cognitive Capabilities of Language Models](https://mlsanity.com/paper/2609.35409/) (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)

## Abstract (arXiv)

A rapidly growing number of applications rely on a small set of closed-source language models (LMs). This dependency might introduce novel security risks if LMs develop self-recognition capabilities. Inspired by human identity verification methods, we propose a novel approach for assessing self-recognition in LMs using model-generated "security questions". Our test can be externally administered to monitor frontier models as it does not require access to internal model parameters or output probabilities. We use our test to examine self-recognition in ten of the most capable open- and closed-source LMs currently publicly available. Our extensive experiments found no empirical evidence of general or consistent self-recognition in any examined LM. Instead, our results suggest that given a set of alternatives, LMs seek to pick the "best" answer, regardless of its origin. Moreover, we find indications that preferences about which models produce the best answers are consistent across LMs. We additionally uncover novel insights on position bias considerations for LMs in multiple-choice settings.