Imagen de Portada

LLMs Position Themselves as More Rational Than Humans: Emergence of AI Self-Awareness Measured Through Game Theory

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Kim, Kyung-Hoon
Formato:	Preprint
Publicado:	2025
Materias:	Artificial Intelligence Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

LLMs Judge Themselves: A Game-Theoretic Framework for Human-Aligned Evaluation
por: Yang, Gao, et al.
Publicado: (2025)

Can LLMs Correct Themselves? A Benchmark of Self-Correction in LLMs
por: Tie, Guiyao, et al.
Publicado: (2025)

When LLMs Benchmark Themselves: Deconstructing Self-Bias in Automated Evaluation
por: Xu, Wenda, et al.
Publicado: (2025)

Can LLMs Explain Themselves Counterfactually?
por: Dehghanighobadi, Zahra, et al.
Publicado: (2025)

LLMs Struggle with Abstract Meaning Comprehension More Than Expected
por: Alhazmi, Hamoud, et al.
Publicado: (2026)

Rethinking Test-Time Scaling for Medical AI: Model and Task-Aware Strategies for LLMs and VLMs
por: Oh, Gyutaek, et al.
Publicado: (2025)

LLMs Can Teach Themselves to Better Predict the Future
por: Turtel, Benjamin, et al.
Publicado: (2025)

LLMs Know More Than Words: A Genre Study with Syntax, Metaphor & Phonetics
por: Shi, Weiye, et al.
Publicado: (2025)

When Models Know More Than They Can Explain: Quantifying Knowledge Transfer in Human-AI Collaboration
por: Shi, Quan, et al.
Publicado: (2025)

When Models Know More Than They Say: Probing Analogical Reasoning in LLMs
por: McGovern, Hope, et al.
Publicado: (2026)

Using Perspectival Words Is Harder Than Vocabulary Words for Humans and Even More So for Multimodal Language Models
por: Dong, Dota Tianai, et al.
Publicado: (2025)

Many LLMs Are More Utilitarian Than One
por: Keshmirian, Anita, et al.
Publicado: (2025)

Refining Positive and Toxic Samples for Dual Safety Self-Alignment of LLMs with Minimal Human Interventions
por: Xu, Jingxin, et al.
Publicado: (2025)

Theory of Mind and Self-Attributions of Mentality are Dissociable in LLMs
por: Kim, Junsol, et al.
Publicado: (2026)

The Algebra of Meaning: Why Machines Need Montague More Than Moore's Law
por: Jeong, Cheonkam, et al.
Publicado: (2025)

Fine-Grained and Thematic Evaluation of LLMs in Social Deduction Game
por: Kim, Byungjun, et al.
Publicado: (2024)

PositionID: LLMs can Control Lengths, Copy and Paste with Explicit Positional Awareness
por: Wang, Zekun, et al.
Publicado: (2024)

Rethinking Layer Redundancy: Calibration Matters More Than Search in LLM Depth Pruning
por: Kim, Minkyu, et al.
Publicado: (2026)

Effects of Theory of Mind and Prosocial Beliefs on Steering Human-Aligned Behaviors of LLMs in Ultimatum Games
por: Yadav, Neemesh, et al.
Publicado: (2025)

Human-AI Collaboration or Academic Misconduct? Measuring AI Use in Student Writing Through Stylometric Evidence
por: Oliveira, Eduardo Araujo, et al.
Publicado: (2025)

When Models Examine Themselves: Vocabulary-Activation Correspondence in Self-Referential Processing
por: Dadfar, Zachary Pedram
Publicado: (2026)

Mind Your Theory: Theory of Mind Goes Deeper Than Reasoning
por: Wagner, Eitan, et al.
Publicado: (2024)

LLMs Know More Than They Show: On the Intrinsic Representation of LLM Hallucinations
por: Orgad, Hadas, et al.
Publicado: (2024)

Language Models can Evaluate Themselves via Probability Discrepancy
por: Xia, Tingyu, et al.
Publicado: (2024)

Trivial Vocabulary Bans Improve LLM Reasoning More Than Deep Linguistic Constraints
por: Jehu-Appiah, Rodney
Publicado: (2026)

More Than a Quick Glance: Overcoming the Greedy Bias in KV-Cache Compression
por: Sood, Aryan, et al.
Publicado: (2026)

Debating with More Persuasive LLMs Leads to More Truthful Answers
por: Khan, Akbir, et al.
Publicado: (2024)

Looking Inward: Language Models Can Learn About Themselves by Introspection
por: Binder, Felix J, et al.
Publicado: (2024)

Are Large Language Models Truly Smarter Than Humans?
por: M, Eshwar Reddy, et al.
Publicado: (2026)

The Self-Execution Benchmark: Measuring LLMs' Attempts to Overcome Their Lack of Self-Execution
por: Ezra, Elon, et al.
Publicado: (2025)

Giving AI Personalities Leads to More Human-Like Reasoning
por: Nighojkar, Animesh, et al.
Publicado: (2025)

More Than Sum of Its Parts: Deciphering Intent Shifts in Multimodal Hate Speech Detection
por: Sun, Runze, et al.
Publicado: (2026)

Tokenization Is More Than Compression
por: Schmidt, Craig W., et al.
Publicado: (2024)

Can Large Language Models Still Explain Themselves? Investigating the Impact of Quantization on Self-Explanations
por: Wang, Qianli, et al.
Publicado: (2026)

Player-Driven Emergence in LLM-Driven Game Narrative
por: Peng, Xiangyu, et al.
Publicado: (2024)

Are More Tokens Rational? Inference-Time Scaling in Language Models as Adaptive Resource Rationality
por: Hu, Zhimin, et al.
Publicado: (2026)

Bounded Rationality for LLMs: Satisficing Alignment at Inference-Time
por: Chehade, Mohamad, et al.
Publicado: (2025)

Helping Large Language Models Protect Themselves: An Enhanced Filtering and Summarization System
por: Muhaimin, Sheikh Samit, et al.
Publicado: (2025)

From Leaky Thoughts to Private Reasoning: Controlling What LRMs Say to Themselves
por: Puerto, Haritz, et al.
Publicado: (2026)

Defend LLMs Through Self-Consciousness
por: Huang, Boshi, et al.
Publicado: (2025)