The Geometry of Ignorance: LLMs Know When to Temper Bayesian Priors

arXiv:2609.02959 · cs.LG, cs.AI, cs.CL, stat.ML · Submitted 2026-09-02 · Read on arXiv

cs.LG, cs.AI, cs.CL, stat.ML

Submitted: 2026-09-02

Updated: 2026-09-02

Terminology

• Transformer — 9× in this paper · explained in 2 episodes
• Steering — 5× in this paper · explained in 2 episodes
• Embeddings — 4× in this paper · explained in 2 episodes
• Accuracy — 3× in this paper · explained in 1 episode
• Bayesian Inference — 3× in this paper · explained in 5 episodes
• Hallucination — 3× in this paper · explained in 3 episodes
• Adam — 2× in this paper · explained in 2 episodes
• Alignment — 1× in this paper · explained in 1 episode
• Bayesian Framework — 1× in this paper · explained in 3 episodes
• Higher-order statistics — 1× in this paper · explained in 2 episodes
• Interpretability — 1× in this paper · explained in 15 episodes
• Objective Function — 1× in this paper · explained in 2 episodes
• Representation Learning — 1× in this paper · explained in 2 episodes
• Workshop on Multi-lingual Representation Learning — 1× in this paper

Sources

• Neural Networks Learn Statistics of Increasing Complexity
• Eliciting Latent Predictions from Transformers with the Tuned Lens
• Universal Neurons in GPT2 Language Models
• Identifying and Mitigating the Influence of the Prior Distribution in Large Language Models

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: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks