mlsanityData to 14 Oct 2026

AI Awareness

arXiv 2504.20084 ↗First posted 25 Apr 2025cs.AI cs.CL cs.CYcited by 7

Not on the map. Why?

Abstract (arXiv)

Recent breakthroughs in artificial intelligence (AI) have brought about increasingly capable systems that demonstrate remarkable abilities in reasoning, language understanding, and problem-solving. These advancements have prompted a renewed examination of AI awareness not as a philosophical question of consciousness, but as a measurable, functional capacity. AI awareness is a double-edged sword: it improves general capabilities, i.e., reasoning, safety, while also raising concerns around misalignment and societal risks, demanding careful oversight as AI capabilities grow. In this review, we explore the emerging landscape of AI awareness, which includes metacognition (the ability to represent and reason about its own cognitive state), self-awareness (recognizing its own identity, knowledge, limitations, inter alia), social awareness (modeling the knowledge, intentions, and behaviors of other agents and social norms), and situational awareness (assessing and responding to the context in which it operates). First, we draw on insights from cognitive science, psychology, and computational theory to trace the theoretical foundations of awareness and examine how the four distinct forms of AI awareness manifest in state-of-the-art AI. Next, we systematically analyze current evaluation methods and empirical findings to better understand these manifestations. Building on this, we explore how AI awareness is closely linked to AI capabilities, demonstrating that more aware AI agents tend to exhibit higher levels of intelligent behaviors. Finally, we discuss the risks associated with AI awareness, including key topics in AI safety, alignment, and broader ethical concerns.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 99 of its 166 references that are in the map. First posted on arXiv 25 Apr 2025.

Builds on

99 of 166 references.

References · 99

  1. 2022Training language models to follow instructions with human feedbackcited by 15,971
  2. 2017Proximal Policy Optimization Algorithmscited by 15,215
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  4. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  5. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  6. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  7. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,386
  8. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  9. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  10. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  11. 2023MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Modelscited by 2,711
  12. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,592
38 more
  1. 2022Emergent Abilities of Large Language Modelscited by 2,512
  2. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,348
  3. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,191
  4. 2023Evaluating Object Hallucination in Large Vision-Language Modelscited by 1,729
  5. 2016Concrete Problems in AI Safetycited by 1,642
  6. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,601
  7. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,395
  8. 2023Large Language Models Cannot Self-Correct Reasoning Yetcited by 1,017
  9. 2022STaR: Bootstrapping Reasoning With Reasoningcited by 940
  10. 2023Large Language Modelscited by 780
  11. 2023Bias and Fairness in Large Language Models: A Surveycited by 639
  12. 2024Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Trainingcited by 529
  13. 2018Towards Robust Interpretability with Self-Explaining Neural Networkscited by 505
  14. 2022LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Actioncited by 439
  15. 2024Training Language Models to Self-Correct via Reinforcement Learningcited by 426
  16. 2025Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Modelscited by 384
  17. 2024Frontier Models are Capable of In-context Schemingcited by 287
  18. 2024Knowledge Conflicts for LLMs: A Surveycited by 283
  19. 2016Rationalizing Neural Predictionscited by 281
  20. 2023Benchmarking and Defending Against Indirect Prompt Injection Attacks on Large Language Modelscited by 264
  21. 2019Risks from Learned Optimization in Advanced Machine Learning Systemscited by 258
  22. 2024LLM Agents Grounded in Self-Reports Enable General-Purpose Simulation of Individualscited by 249
  23. 2023Do Large Language Models Know What They Don't Know?cited by 243
  24. 2016A Persona-Based Neural Conversation Modelcited by 223
  25. 2023Evaluating Large Language Models in Theory of Mind Taskscited by 222
  26. 2023An Overview of Catastrophic AI Riskscited by 222
  27. 2023Universal Self-Consistency for Large Language Model Generationcited by 203
  28. 2023AI Deception: A Survey of Examples, Risks, and Potential Solutionscited by 188
  29. 2018The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigationcited by 165
  30. 2023Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentationcited by 147
  31. 2023Large Language Models can Strategically Deceive their Users when Put Under Pressurecited by 146
  32. 2024AI Sandbagging: Language Models can Strategically Underperform on Evaluationscited by 145
  33. 2023Taken out of context: On measuring situational awareness in LLMscited by 143
  34. 2024Looking Inward: Language Models Can Learn About Themselves by Introspectioncited by 113
  35. 2023The Earth is Flat because...: Investigating LLMs' Belief towards Misinformation via Persuasive Conversationcited by 109
  36. 2023Mindstorms in Natural Language-Based Societies of Mindcited by 107
  37. 2023Deception Abilities Emerged in Large Language Modelscited by 101
  38. 2024Large Language Models Must Be Taught to Know What They Don't Knowcited by 100

50 most cited of 99 All 99 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 4.

7 papers.

  1. 2025Know Thyself? On the Incapability and Implications of AI Self-Recognitioncited by 8
  2. 2025Towards Understanding the Cognitive Habits of Large Reasoning Modelscited by 4
  3. 2026No Reliable Evidence of Self-Reported Sentience in Small Large Language Modelscited by 3
  4. 2026Steerability of Instrumental-Convergence Tendencies in LLMscited by 1
  5. 2026Metacognition in LLMs: Foundations, Progress, and Opportunitiescited by 1
  6. 2025Natural, Artificial, and Human Intelligencescited by 0
  7. 2026AwarenessBench: Assessing Cognitive Capabilities of Language Modelscited by 0