Prune to Probe: Causal Decision-Stability Probes for Efficient Reasoning
cs.LG
Submitted: 2026-11-08
Updated: 2026-11-08
Code: https://github.com/YQ-HA/prune_to_probe
Terminology
Sources
- LAQuant: A Simple Overhead-free Large Reasoning Model Quantization by Layer-wise Lookahead Loss
- Training Verifiers to Solve Math Word Problems
- OS-Pruner: Pruning Chains-of-Thought of Reasoning Models via Optimal Stopping
- Pruning Large Language Models by Identifying and Preserving Functional Networks
- Pruning via Causal Attribution Preserves Reasoning Performance in Large Language Models
- Think Before You Prune: Selective Self-Generated Calibration for Pruning Large Reasoning Models
- Qwen3 Technical Report
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