The paper revisits the impact of pruning on large language models (LLMs) during test-time scaling (TTS). While prior work found that structured pruning degrades reasoning performance, this study shows that unstructured pruning—removing only specific redundant weights—can actually improve TTS performance on reasoning benchmarks for models s1.1-7B and Qwen3-8B, sometimes surpassing the full-weight models. The authors also examine how different layer-wise sparsity allocation strategies affect these outcomes.
arXiv:2510. 22228v2 Announce Type: replace-cross Abstract: Layer pruning has emerged as a widely adopted technique for improving the efficiency of large language models (LLMs).
arXiv:2504.04342v2 Announce Type: replace Abstract: Scaling up model parameters and training data consistently improves the performance of large language models (LLMs), but at the cost of rapidly gro...
arXiv:2605. 18331v2 Announce Type: replace Abstract: Large Language Models (LLMs) have experienced significant growth and development in recent years.
OBC‑Prune introduces an outcome‑based calibration approach for pruning large reasoning models, focusing on the causal importance of each reasoning sentence rather than uniform activation salience. By pairing correct and incorrect rollouts and using intervention‑based analysis, it assigns per‑token weights that guide one‑shot pruning methods such as SparseGPT, Wanda, and ALPS. Experiments on DeepSeek‑R1‑Distill‑Qwen models show consistent accuracy gains and shorter reasoning traces across multiple benchmarks at 40‑50% sparsity.
arXiv:2509.14093v3 Announce Type: replace-cross Abstract: Chain-of-Thought (CoT) prompting can substantially improve the reasoning ability of large language models (LLMs), but it often comes with hig...
arXiv:2607. 18280v1 Announce Type: cross Abstract: Large language models (LLMs) are often compressed through static parameter pruning or dynamic token-level computation, yet aggressive sparsification can trigger rapid performance degradation beyond an essential sparsity boundary.
arXiv:2602. 01997v3 Announce Type: replace-cross Abstract: Recent work has shown that layer pruning can effectively compress large language models (LLMs) while retaining strong performance on classification benchmarks, often with little or no finetuning.
arXiv:2606. 09080v1 Announce Type: new Abstract: Pruning has emerged as a dominant paradigm for accelerating large language model (LLM) inference, spanning a broad spectrum of methods that remove computation across tokens, layers, heads, dimensions, and attention patterns.
arXiv:2602. 06127v2 Announce Type: replace Abstract: The high computational demands of Large Language Models (LLMs) motivate methods that reduce parameter count and accelerate inference.
The paper presents a systematic study of how different compression techniques—pruning, quantization, and distillation—affect the capabilities of large language models (LLMs) in tasks such as mathematics, code generation, and question answering. It introduces a framework that measures capability loss and relates it to factors like model size, training stage, and compression settings, yielding simple predictive relations that generalize across unseen configurations. The authors demonstrate that sharing density responses across pruning levels can dramatically reduce the number of measurements needed, and that their predictive models closely match regression results while offering efficient decision guidance for compression method selection.
arXiv:2507. 01900v3 Announce Type: replace-cross Abstract: Pruning is a highly effective approach for compressing large language models (LLMs), significantly reducing inference latency.
arXiv:2606. 07819v1 Announce Type: new Abstract: Recently, the efficiency of Large Language Models (LLMs) deployment has become a critical concern in practical applications.