What pass@k Cannot Measure: Evaluating Diversity and Capability Retention after Post-Training
cs.LG
Submitted: 2026-10-05
Updated: 2026-10-05
Sources
- Evaluating Large Language Models Trained on Code
- Training Verifiers to Solve Math Word Problems
- Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?
- QUATRO: Query-Adaptive Trust Region Policy Optimization for LLM Fine-tuning
- Let's Verify Step by Step
- On-Policy Self-Distillation with Sampled Demonstrations Reduces Output Diversity
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?
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