Bayesian Fine-tuning Yields Language Models that are as Bayesian as their Beliefs Allow

arXiv:2610.00679 · cs.CL · Submitted 2026-09-30 · Read on arXiv

cs.CL

Submitted: 2026-09-30

Updated: 2026-09-30

Comments: under review, 27 pages, 25 figures

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Accuracy — 68× in this paper · explained in 1 episode
• Fine-Tuning — 23× in this paper · explained in 5 episodes
• Consistency — 14× in this paper · explained in 3 episodes
• Bayesian Inference — 13× in this paper · explained in 5 episodes
• Steering — 13× in this paper · explained in 2 episodes
• In-Context Learning — 4× in this paper · explained in 4 episodes
• Linear probe — 4× in this paper · explained in 2 episodes
• Generative AI — 3× in this paper · explained in 2 episodes
• Activation Addition — 2× in this paper · explained in 1 episode
• Adam — 2× in this paper · explained in 2 episodes
• Alignment — 2× in this paper · explained in 1 episode
• Decode — 2× in this paper · explained in 2 episodes
• Activation Steering — 1× in this paper · explained in 4 episodes
• Actor — 1× in this paper · explained in 3 episodes
• Agentic AI — 1× in this paper · explained in 1 episode
• Alignment Theory — 1× in this paper · explained in 1 episode
• Bayesian Framework — 1× in this paper · explained in 3 episodes
• Benchmark — 1× in this paper · explained in 2 episodes
• Calibration — 1× in this paper · explained in 7 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Hallucination — 1× in this paper · explained in 3 episodes
• Interpretability — 1× in this paper · explained in 15 episodes
• National Science Foundation — 1× in this paper
• Scaffolding — 1× in this paper · explained in 3 episodes
• Supervised Fine-Tuning (SFT) — 1× in this paper · explained in 8 episodes
• Transformer — 1× in this paper · explained in 2 episodes

Sources

• Belief Dynamics Reveal the Dual Nature of In-Context Learning and Activation Steering
• Brittle Minds, Fixable Activations: Understanding Belief Representations in Language Models
• Is In-Context Learning in Large Language Models Bayesian? A Martingale Perspective
• Inside-Out: Hidden Factual Knowledge in LLMs
• The Llama 3 Herd of Models
• Large Language Models Assume People are More Rational than We Really are
• Reasoning over Uncertain Text by Generative Large Language Models
• Constrained belief updates explain geometric structures in transformer representations
• Reasoning Under Uncertainty: Exploring Probabilistic Reasoning Capabilities of LLMs
• Qwen2.5 Technical Report
• BayesBench: Evaluating LLM Belief Trajectories Under Multi-Turn Evidence Accumulation
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• Gemma 2: Improving Open Language Models at a Practical Size
• Function Vectors in Large Language Models
• Instructions Shape Production of Language, not Processing
• An Explanation of In-context Learning as Implicit Bayesian Inference
• What and How does In-Context Learning Learn? Bayesian Model Averaging, Parameterization, and Generalization
• Incoherent Probability Judgments in Large Language Models

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering