Understanding as No-Arbitrage: Bounded Dutch Books as a Definition and Training Objective for Language Models
cs.AI, cs.CL, cs.LG
Submitted: 2026-09-30
Updated: 2026-09-30
Terminology
Sources
- Revealed Rationality: Label-Free Evaluation and Regularization from Representation Theorems
- Dutch Books for Language Models
- Strong hallucinations from negation and how to fix them
- Logically Consistent Language Models via Neuro-Symbolic Integration
- Credal Bayesian Deep Learning
- Credal Large Language Models for Semantic Commitment under Uncertainty
- CreINNs: Credal-Set Interval Neural Networks for Uncertainty Estimation in Classification Tasks
- Logical Induction
- Precise Propagation of Upper and Lower Probability Bounds in System P
- LLMs are not (consistently) Bayesian: Quantifying internal (in)consistencies of LLMs' probabilistic beliefs
- Logical GANs: Adversarial Learning through Ehrenfeucht Fraisse Games
- Generative Adversarial Reasoner: Enhancing LLM Reasoning with Adversarial Reinforcement Learning
- Self-CTRL: Self-Consistency Training with Reinforcement Learning
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