LAVOIR: Teaching a Single-Pass Decision Encoder When and What to Ask with Amortized Value of Information

arXiv:2609.30706 · cs.AI, cs.CL · Submitted 2026-09-25 · Read on arXiv

cs.AI, cs.CL

Submitted: 2026-09-25

Updated: 2026-09-25

Code: https://github.com/AbdelStark/jev-ben

Terminology

• Accuracy — 23× in this paper · explained in 1 episode
• Benchmark — 17× in this paper · explained in 2 episodes
• AUC — 12× in this paper · explained in 2 episodes
• Calibration — 7× in this paper · explained in 7 episodes
• AUROC — 2× in this paper · explained in 2 episodes
• Adam — 2× in this paper · explained in 2 episodes
• Conformal Prediction — 2× in this paper · explained in 5 episodes
• RAG — 2× in this paper · explained in 3 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Ablation — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Decode — 1× in this paper · explained in 2 episodes
• Deferral — 1× in this paper · explained in 2 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Information Gain — 1× in this paper · explained in 2 episodes
• Ontology — 1× in this paper · explained in 2 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Uncertainty Quantification — 1× in this paper · explained in 8 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• STaR-GATE: Teaching Language Models to Ask Clarifying Questions
• A Gentle Introduction to Conformal Prediction and Distribution-Free Uncertainty Quantification
• Program Synthesis with Large Language Models
• MS MARCO: A Human Generated MAchine Reading COmprehension Dataset
• Training Verifiers to Solve Math Word Problems
• Gemma 4 Technical Report
• Uncertainty of Thoughts: Uncertainty-Aware Planning Enhances Information Seeking in Large Language Models
• Measuring a hate speech spectrum with faceted Rasch item response theory and perspective-aware, explainable-by-design deep learning
• CLAM: Selective Clarification for Ambiguous Questions with Generative Language Models
• mmBERT: A Modern Multilingual Encoder with Annealed Language Learning
• RouteLLM: Learning to Route LLMs with Preference Data
• Robots That Ask For Help: Uncertainty Alignment for Large Language Model Planners
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• SCX Router: Streaming Zero-Shot Model Selection with a Decoder-KV Classifier and a Real-World Task Ontology
• GLiClass: Generalist Lightweight Model for Sequence Classification Tasks
• Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference
• Qwen3 Technical Report
• MoganBert-TR: A Turkish Encoder Foundation Model Trained from Scratch with a CLM-to-MLM Curriculum
• Clarify When Necessary: Resolving Ambiguity Through Interaction with LMs

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