Learning What to Ask and What to Believe: Distilling a Variational Bayesian Agent into Language Models
cs.LG
Submitted: 2026-10-31
Updated: 2026-10-31
Terminology
Sources
- CA-BED: Conversation-Aware Bayesian Experimental Design
- Multi-Turn Puzzles: Evaluating Interactive Reasoning and Strategic Dialogue in LLMs
- BED-LLM: Intelligent Information Gathering with LLMs and Bayesian Experimental Design
- Uncertainty-Aware Clarification in LLM Agents with Information Gain
- The Llama 3 Herd of Models
- Bayesian Preference Elicitation with Language Models
- Amortising Bayesian Experimental Design for Sequential Information Gathering in LLMs
- Distilling the Knowledge in a Neural Network
- Bayesian Active Learning for Classification and Preference Learning
- Failing to Falsify: Evaluating and Mitigating Confirmation Bias in Language Models
- DRILL: Training World Models to Improve Policies, Not Predict Pixels
- CLAM: Selective Clarification for Ambiguous Questions with Generative Language Models
- LLMs Get Lost In Multi-Turn Conversation
- Show Your Work: Scratchpads for Intermediate Computation with Language Models
- Active Preference Inference using Language Models and Probabilistic Reasoning
- Bayesian Teaching Enables Probabilistic Reasoning in Large Language Models
- PAR: Progress-Aligned Recurrence for Length Generalization in State Tracking
- Clarify When Necessary: Resolving Ambiguity Through Interaction with LMs
- Reducing Belief Deviation in Reinforcement Learning for Active Reasoning
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis