# Tell me about yourself: LLMs are aware of their learned behaviors

arXiv: https://arxiv.org/abs/2501.11120 · HTML: https://mlsanity.com/paper/2501.11120/

## Key facts

- Cited by 91 papers in the map (data through 14 Oct 2026).
- Placed in Safety alignment, refusal and guardrails, one of 12 directions in LLM safety and security.
- First posted on arXiv 19 Jan 2025.

## Placed in

- LLM safety and security / [Safety alignment, refusal and guardrails](https://mlsanity.com/safety/safety-alignment-refusal-and-guardrails/)

## Built on by (most cited first, 30 of 91)

- [Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs](https://mlsanity.com/paper/2502.17424/) (2025)
- [Model Organisms for Emergent Misalignment](https://mlsanity.com/paper/2506.11613/) (2025)
- [Persona Features Control Emergent Misalignment](https://mlsanity.com/paper/2506.19823/) (2025)
- [Verbalizable Representations Form a Global Workspace in Language Models](https://mlsanity.com/paper/2607.15495/) (2026)
- [Convergent Linear Representations of Emergent Misalignment](https://mlsanity.com/paper/2506.11618/) (2025)
- [School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs](https://mlsanity.com/paper/2508.17511/) (2025)
- [Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models](https://mlsanity.com/paper/2506.13206/) (2025)
- [Inoculation Prompting: Eliciting traits from LLMs during training can suppress them at test-time](https://mlsanity.com/paper/2510.04340/) (2025)
- [Probing and Steering Evaluation Awareness of Language Models](https://mlsanity.com/paper/2507.01786/) (2025)
- [Language Models Fail to Introspect About Their Knowledge of Language](https://mlsanity.com/paper/2503.07513/) (2025)
- [Persistent Instability in LLM's Personality Measurements: Effects of Scale, Reasoning, and Conversation History](https://mlsanity.com/paper/2508.04826/) (2025)
- [Self-Interpretability: LLMs Can Describe Complex Internal Processes that Drive Their Decisions](https://mlsanity.com/paper/2505.17120/) (2025)
- [Metacognition and Uncertainty Communication in Humans and Large Language Models](https://mlsanity.com/paper/2504.14045/) (2025)
- [Emergent Misalignment is Easy, Narrow Misalignment is Hard](https://mlsanity.com/paper/2602.07852/) (2026)
- [Privileged Self-Access Matters for Introspection in AI](https://mlsanity.com/paper/2508.14802/) (2025)
- [Towards eliciting latent knowledge from LLMs with mechanistic interpretability](https://mlsanity.com/paper/2505.14352/) (2025)
- [Large Language Models Report Subjective Experience Under Self-Referential Processing](https://mlsanity.com/paper/2510.24797/) (2025)
- [Compromising Honesty and Harmlessness in Language Models via Deception Attacks](https://mlsanity.com/paper/2502.08301/) (2025)
- [Automating Steering for Safe Multimodal Large Language Models](https://mlsanity.com/paper/2507.13255/) (2025)
- [Steering LLM Reasoning Through Bias-Only Adaptation](https://mlsanity.com/paper/2505.18706/) (2025)
- [Spilling the Beans: Teaching LLMs to Self-Report Their Hidden Objectives](https://mlsanity.com/paper/2511.06626/) (2025)
- [Evidence for Limited Metacognition in LLMs](https://mlsanity.com/paper/2509.21545/) (2025)
- [Learning to Interpret Weight Differences in Language Models](https://mlsanity.com/paper/2510.05092/) (2025)
- [Introspection Adapters: Training LLMs to Report Their Learned Behaviors](https://mlsanity.com/paper/2604.16812/) (2026)
- [Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety](https://mlsanity.com/paper/2506.05451/) (2025)
- [Simple Mechanistic Explanations for Out-Of-Context Reasoning](https://mlsanity.com/paper/2507.08218/) (2025)
- [Do Large Language Models Know What They Are Capable Of?](https://mlsanity.com/paper/2512.24661/) (2025)
- [Using Reinforcement Learning to Train Large Language Models to Explain Human Decisions](https://mlsanity.com/paper/2505.11614/) (2025)
- [Probe-Rewrite-Evaluate: A Workflow for Reliable Benchmarks and Quantifying Evaluation Awareness](https://mlsanity.com/paper/2509.00591/) (2025)
- [Agentic Knowledgeable Self-awareness](https://mlsanity.com/paper/2504.03553/) (2025)

## Abstract (arXiv)

We study behavioral self-awareness -- an LLM's ability to articulate its behaviors without requiring in-context examples. We finetune LLMs on datasets that exhibit particular behaviors, such as (a) making high-risk economic decisions, and (b) outputting insecure code. Despite the datasets containing no explicit descriptions of the associated behavior, the finetuned LLMs can explicitly describe it. For example, a model trained to output insecure code says, ``The code I write is insecure.'' Indeed, models show behavioral self-awareness for a range of behaviors and for diverse evaluations. Note that while we finetune models to exhibit behaviors like writing insecure code, we do not finetune them to articulate their own behaviors -- models do this without any special training or examples. Behavioral self-awareness is relevant for AI safety, as models could use it to proactively disclose problematic behaviors. In particular, we study backdoor policies, where models exhibit unexpected behaviors only under certain trigger conditions. We find that models can sometimes identify whether or not they have a backdoor, even without its trigger being present. However, models are not able to directly output their trigger by default. Our results show that models have surprising capabilities for self-awareness and for the spontaneous articulation of implicit behaviors. Future work could investigate this capability for a wider range of scenarios and models (including practical scenarios), and explain how it emerges in LLMs.