How Proper Scoring Rules Shape LLM Forecasting
cs.LG, cs.AI
Submitted: 2026-08-28
Updated: 2026-09-09
Comments: Added a three-seed replication of the Log and Brier reward conditions, including forecasting metrics and BIN analysis
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Approaching Human-Level Forecasting with Language Models
- Confronting Reward Model Overoptimization with Constrained RLHF
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Future-as-Label: Scalable Supervision from Real-World Outcomes
- Forecasting Future World Events with Neural Networks
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: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks