User Model Extraction via Belief Self-Distillation
cs.LG, cs.CL
Submitted: 2026-09-25
Updated: 2026-09-25
Code: https://github.com/holmov1/bsd-user-models
Terminology
Sources
- Persona Vectors: Monitoring and Controlling Character Traits in Language Models
- Designing a Dashboard for Transparency and Control of Conversational AI
- Do LLMs Experience an Internal Polylogue? Investigating Reasoning through the Lens of Personas
- Distilling the Knowledge in a Neural Network
- Similarity of Neural Network Representations Revisited
- Olmo 3
- Qwen3 Technical Report
- Locating and Controlling Implicit Personalization 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