Nudgeability: Reasoning Models Follow Confidence Signals Without Tracking Their Own Competence
cs.AI, cs.CL, cs.LG
Submitted: 2026-09-28
Updated: 2026-09-28
Terminology
Sources
- Can LLMs Predict Their Own Failures? Self-Awareness via Internal Circuits
- LLMs Should Express Uncertainty Explicitly
- Language Models (Mostly) Know What They Know
- Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMs
- Measuring Faithfulness in Chain-of-Thought Reasoning
- Who Flips? Self- and Cross-Model Counterarguments Reveal Answer Instability in LLMs
- There Will Be a Scientific Theory of Deep Learning
- Privileged Self-Access Matters for Introspection in AI
- To Call or Not to Call: A Framework to Assess and Optimize LLM Tool Calling
- Effectively Controlling Reasoning Models through Thinking Intervention
- Dynamic Early Exit in Reasoning Models
- ReAct: Synergizing Reasoning and Acting in Language Models
- Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection