Learned Reporting Preferences in RLVR Can Conflict with the Current Request
cs.LG
Submitted: 2026-09-29
Updated: 2026-09-29
Code: https://github.com/huggingface/Math-Verify
Sources
- SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model
- Evaluating Large Language Models Trained on Code
- Training Verifiers to Solve Math Word Problems
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Measuring Mathematical Problem Solving With the MATH Dataset
- A Sober Look at Progress in Language Model Reasoning: Pitfalls and Paths to Reproducibility
- From Accuracy to Robustness: A Study of Rule- and Model-based Verifiers in Mathematical Reasoning
- Tulu 3: Pushing Frontiers in Open Language Model Post-Training
- Understanding R1-Zero-Like Training: A Critical Perspective
- 2 OLMo 2 Furious
- Qwen2.5 Technical Report
- Proximal Policy Optimization Algorithms
- Spurious Rewards: Rethinking Training Signals in RLVR
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- The Invisible Leash: Why RLVR May or May Not Escape Its Origin
- Outcome Rewards Do Not Guarantee Verifiable or Causally Important Reasoning
- Instruction-Following Evaluation for 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: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks