Anosognosia in LLMs: Probing Self-Awareness of Quantized Computational Substrate
cs.LG, cs.AI, cs.CL, cs.CY
Submitted: 2026-10-05
Updated: 2026-10-05
Code: https://github.com/Omusubi0123/llm-anosognosia
Sources
- Taken out of context: On measuring situational awareness in LLMs
- Are You Getting What You Pay For? Auditing Model Substitution in LLM APIs
- How is ChatGPT's behavior changing over time?
- The Llama 3 Herd of Models
- Emergent Introspective Awareness in Large Language Models
- Metacognition in LLMs: Foundations, Progress, and Opportunities
- Can LLMs Introspect? A Reality Check
- Gemma 3 Technical Report
- Qwen3 Technical Report
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks