Training Autoregressive Language Models on Rounded, Bounded, and Censored Numerical Labels via Exact Likelihood
cs.LG
Submitted: 2026-11-02
Updated: 2026-11-17
Terminology
Sources
- Regression Language Models for Code
- Probabilistic Calibration Is a Trainable Capability in Language Models
- PATH: Next-Interval Prediction via Autoregressive Tree Hierarchy on Tabular Data
- Beyond Token-level Supervision: Unlocking the Potential of Decoding-based Regression via Reinforcement Learning
- Reinforcement Learning over Predictive Distributions for LLM Regression
- Eliciting Numerical Predictive Distributions of LLMs Without Autoregression
- Language Generation with Strictly Proper Scoring Rules
- Decoding-based Regression
- Deep Nonparametric Estimation of Discrete Conditional Distributions via Smoothed Dyadic Partitioning
- Towards end-to-end LLM-based censoring-aware survival analysis
- Qwen3 Technical Report
- NumericJev: Jev-like LLM Numerical Decoding with Multiway Decision Trees
- Regress, Don't Guess -- A Regression-like Loss on Number Tokens for Language Models
- DEL: Digit Entropy Loss for Numerical Learning of Large Language Models
- Enhancing Numerical Prediction in LLMs via Smooth MMD Alignment
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