Rethinking LLM Pruning via Test-Time Scaling
cs.CL
Submitted: 2026-10-31
Updated: 2026-10-31
Code: https://github.com/nick7nlp/RAZOR
Terminology
Sources
- Large Language Monkeys: Scaling Inference Compute with Repeated Sampling
- Evaluating Large Language Models Trained on Code
- Accuracy is Not All You Need
- Gemma 4 Technical Report
- Compressing LLMs: The Truth is Rarely Pure and Never Simple
- Finding Fantastic Experts in MoEs: A Unified Study for Expert Dropping Strategies and Observations
- REAM: Merging Improves Pruning of Experts in LLMs
- ReCal: Calibrating Structured Pruning for On-Policy Distillation Recovery
- The Llama 3 Herd of Models
- Revisiting the Effectiveness of LLM Pruning for Test-Time Scaling
- A Survey of On-Policy Distillation for Large Language Models
- RAZOR: Pruning Replaceable Experts in LLMs
- UniComp: A Unified Evaluation of Large Language Model Compression via Pruning, Quantization, and Distillation
- When Fewer Layers Break More Chains: Layer Pruning Harms Test-Time Scaling in LLMs
- Self-Consistency Improves Chain of Thought Reasoning in Language Models
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data