LLM Pruning

LLM: Large Language Model

Ask about this topic

Momentum

12 papers in the last four weeks, up 200% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 113

All topics
CardsList
May 2, 2026cs.LG

Weight Pruning Amplifies Bias: A Multi-Method Study of Compressed LLMs for Edge AI

Weight pruning is widely advocated for deploying Large Language Models on resource-constrained IoT and edge devices, yet its impact on model fairness remains poorly understood. We conduct a controlled empirical study of three instruction-tuned models (Gemma-2-9b-it, Mistral-7B-Instruct-v0.3, Phi-3.5-mini-instruct) across three pruning methods (Random, Magnitude, Wanda) at four sparsity levels (10-70%) on 12,148 BBQ bias benchmark items with 5 random seeds, totaling 2,368,860 inference records. Our results reveal a Smart Pruning Paradox: activation-aware pruning (Wanda) preserves perplexity nearly perfectly (just 3.5% increase at 50% sparsity for Mistral-7B), yet produces the highest bias amplification, with Stereotype Reliance Score increasing 83.7% and 47-59% of previously unbiased items developing new stereotypical behaviors at 70% sparsity. Random pruning destroys language capability entirely (perplexity exceeding 10410^4 and reaching 10810^8) but produces only random-chance bias. We further show that unstructured pruning provides zero storage savings and zero inference latency reduction on real edge hardware, undermining the primary motivation for its use in IoT deployment. Of 180 dense-vs-pruned comparisons, 141 (78.3%) are significant (p<0.05p < 0.05) with mean ∣h∣=0.305|h| = 0.305. Published quantization studies report up to 21% of responses flipping between biased and unbiased states; our pruning results show transition rates nearly three times higher (47-59%), suggesting pruning poses a categorically greater risk to alignment than quantization. These findings demonstrate that perplexity-based evaluation provides false assurance of behavioral equivalence, and that IoT deployment pipelines require bias-aware validation before deploying pruned models at the edge.

Plawan Kumar Rath, Rahul Maliakkal

Meta

LLM PruningOn-Device Language Model InferenceSocial Bias in Language ModelsLanguage Model Bias Evaluation
AskPDF
Apr 29, 2026cs.CL

Exploring the Limits of Pruning: Task-Specific Neurons, Model Collapse, and Recovery in Task-Specific Large Language Models

Neuron pruning is widely used to reduce the computational cost and parameter footprint of large language models, yet it remains unclear whether neurons in task-specific models contribute uniformly to task performance. In this work, we provide empirical evidence for the existence and importance of task-specific neurons through a systematic pruning study on language models specialized for mathematical reasoning and code generation. We introduce an activation-based selectivity metric to identify neurons with low contribution to the target task and prune them while preserving target-task accuracy, and compare selective pruning with random pruning. Selective pruning consistently outperforms random pruning, indicating that activation-based selectivity provides a systematic advantage over random pruning. Reverse pruning experiments further show that removing a small subset of highly task-specific neurons (~10%) causes complete performance collapse, suggesting that there exist task specific neurons and critical task information is concentrated in a small portion of the network. In contrast, selective pruning of less critical neurons (~30% - ~35%) reduces accuracy but still preserves significant performance. We also observed consistent reductions in parameters and runtime VRAM usage, along with improved inference throughput as pruning increases. Experiments on both 1.5B and 7B models reveal a robustness threshold around 15-20% pruning, beyond which accuracy loss and generation failures increase sharply. Fine-tuning substantially recovers performance across pruning levels, particularly for aggressively pruned models. These findings provide empirical evidence of neuron specialization in task-specific language models and offer insights into pruning robustness, model redundancy, and post-pruning recoverability.

M. K. Khalidi Siam, Md. Tausif-Ul-Islam, Md. Reshad Romim Khan +5

1BRAC University

LLM PruningLanguage ModelingNeural Network Pruning
AskPDF
Apr 28, 2026cs.AI

Revisiting the Effectiveness of LLM Pruning for Test-Time Scaling

Large Language Models (LLMs) now exhibit remarkable reasoning capabilities through test-time compute scaling (TTS), with impressive performance across math and coding benchmarks. In parallel, research in model compression has developed pruning methods that seek to remove redundant/detrimental parameters without sacrificing task performance. The intersection of these two research advancements lays the foundation for our work. Specific to reasoning LLMs, prior work has shown that structured pruning (methods which remove entire set of layer blocks), significantly degrades TTS reasoning performance. However, in this work, we revisit this assumption and investigate whether unstructured pruning (methods that carefully remove only certain redundant/detrimental weights) exhibits similar limitations. Surprisingly, our extensive experiments across four reasoning benchmarks on two reasoning LLMs: s1.1-7B and Qwen3-8B, consistently show that unstructured pruning augments TTS performance compared to structured pruning, and at times can even outperform the unpruned full-weight LLMs. Furthermore, we also empirically study the impact of different layer-wise sparsity allocation strategies, which are an important parametric choice for instantiating these unstructured methods. These findings challenge the conventional notion that pruning always reduces TTS performance and in fact, suggest that carefully undertaken pruning can retain TTS effectiveness.

Ocean Monjur, Shahriar Kabir Nahin, Anshuman Chhabra

Bellini College of AI, Cybersecurity, and Computing University of South Florida Tampa, FL, USA

LLM PruningTest-Time ScalingNeural Network Pruning
AskPDF
Apr 27, 2026cs.LG

Rethinking Layer Redundancy: Calibration Matters More Than Search in LLM Depth Pruning

Depth pruning improves the inference efficiency of large language models by removing Transformer blocks. Prior work typically treats layer redundancy as an inherent structural property of pretrained networks, emphasizing importance criteria and search algorithms to identify removable layers. In this study, we empirically investigate depth pruning from a functional perspective. Evaluating representative LLM families across diverse calibration configurations and multiple search algorithms, we show that different configurations produce different pruning patterns. Furthermore, under a fixed calibration configuration, complex search algorithms yield marginal performance improvements over simple one-shot methods, converging to similar pruned subsets. Overall, our results suggest that the calibration configuration plays a substantially larger role than the choice of search algorithm in shaping pruning patterns and calibration perplexity, while contributing comparably to variance in downstream reasoning accuracy. This indicates that future pruning efforts may benefit from prioritizing the calibration configuration over search complexity.

Minkyu Kim, Vincent-Daniel Yun, Youngrae Kim +3

Neural Superintelligence Lab, MODULABS, Republic of Korea · University of Southern California, United States · Boston University, United States +2

LLM PruningLLM Inference AccelerationNeural Network Pruning
AskPDF
Apr 27, 2026cs.CL

DepthKV: Layer-Dependent KV Cache Pruning for Long-Context LLM Inference

Long-context reasoning is a critical capability of large language models (LLMs), enabling applications such as long-document understanding, summarization, and code generation. However, efficient autoregressive inference relies on the key-value (KV) cache, whose memory footprint grows linearly with sequence length, leading to a major memory bottleneck. To mitigate this overhead, KV cache pruning methods discard cached tokens with low attention scores during inference. Most existing methods apply a uniform pruning ratio across layers, implicitly assuming that all layers contribute equally to overall model performance. We show that this assumption is suboptimal, as layers differ significantly in their sensitivity to pruning. We propose DepthKV, a layer-dependent pruning framework that allocates a fixed global KV budget across layers based on their sensitivity, rather than using a uniform allocation. Across multiple models and tasks, DepthKV consistently outperforms uniform pruning at the same global pruning ratio, demonstrating more effective utilization of the KV cache budget through layer-dependent allocation.

Zahra Dehghanighobadi, Asja Fischer

1Ruhr University Bochum · 2UAR Research Center for Trustworthy Data Science and Security

LLM PruningKV CachingLong-Context Language Model InferenceKV-Cache ManagementMemory-Efficient InferenceKV-Cache Pruning
AskPDF
Apr 27, 2026cs.CL

Pruning via Causal Attribution Preserves Reasoning Performance in Large Language Models

Large language models (LLMs) excel at multi-step reasoning but incur substantial inference cost. We introduce Causal Attribution Pruning (CAP), a training-free method that identifies critical attention heads by measuring their causal impact on reasoning tasks and uses these head-level scores to guide fine-grained weight pruning. For each attention head, CAP estimates the expected performance degradation when the head is masked during forward passes on a small calibration set of reasoning problems. These causal scores are then converted into weight-level importance values for the corresponding projection matrices. Unlike magnitude-only or activation-based criteria, CAP's interventional measurement directly captures each head's functional contribution, yielding relative accuracy gains of up to 61% over Wanda on ARC-Challenge at 20% sparsity. We evaluate CAP on GSM8K, StrategyQA, and ARC-Challenge using Llama-3-8B-Instruct and Mistral-7B-Instruct at 10%, 20%, and 50% sparsity. At moderate sparsity (10-20%), CAP improves over Wanda in most model-benchmark configurations. with especially large gains on ARC-Challenge for Llama-3. Our results suggest that attention-head-level causal attribution can better preserve reasoning performance on downstream benchmarks than correlational pruning criteria at equivalent sparsity, while remaining limited by coarse MLP attribution at 50% sparsity.

Amogh Sheth, Biruk Assefa, Yi Wen Huang +2

Edison Academy Magnet School · State University of New York College at Plattsburgh · The University of Texas at Austin +2

LLM PruningSelf-AttentionLLM Inference AccelerationAttention MechanismsAttention Head PruningCausal Interventions in Language Models+2
AskPDF
Apr 26, 2026cs.LG

Supernodes and Halos: Loss-Critical Hubs in LLM Feed-Forward Layers

We study the organization of channel-level importance in transformer feed-forward networks (FFNs). Using a Fisher-style loss proxy (LP) based on activation-gradient second moments, we show that loss sensitivity is concentrated in a small set of channels within each layer. In Llama-3.1-8B, the top 1% of channels per layer accounts for a median of 58.7% of LP mass, with a range of 33.0% to 86.1%. We call these loss-critical channels supernodes. Although FFN layers also contain strong activation outliers, LP-defined supernodes overlap only weakly with activation-defined outliers and are not explained by activation power or weight norms alone. Around this core, we find a weaker but consistent halo structure: some non-supernode channels share the supernodes' write support and show stronger redundancy with the protected core. We use one-shot structured FFN pruning as a diagnostic test of this organization. At 50% FFN sparsity, baselines that prune many supernodes degrade sharply, whereas our SCAR variants explicitly protect the supernode core; the strongest variant, SCAR-Prot, reaches perplexity 54.8 compared with 989.2 for Wanda-channel. The LP-concentration pattern appears across Mistral-7B, Llama-2-7B, and Qwen2-7B, remains visible in targeted Llama-3.1-70B experiments, and increases during OLMo-2-7B pretraining. These results suggest that LLM FFNs develop a small learned core of loss-critical channels, and that preserving this core is important for reliable structured pruning.

Audrey Cherilyn, Houman Safaai

Kempner Institute at Harvard University

Transformer InterpretabilityLLM PruningTransformer FFNsNeural Network Pruning
AskPDF
Apr 21, 2026cs.AI

SimDiff: Depth Pruning via Similarity and Difference

Depth pruning improves the deployment efficiency of large language models (LLMs) by identifying and removing redundant layers. A widely accepted standard for this identification process is to measure the similarity between layers using cosine distance. However, we find that methods relying solely on this one-dimensional heuristic can exhibit unpredictable performance and even catastrophic collapse across different architectures. To address this issue, we propose SimDiff, a novel layer importance criterion that jointly evaluates layers from two orthogonal perspectives: representational similarity and transformation difference. The difference is quantified using two distinct metrics: MSSD, which is sensitive to outliers and identifies layers that make decisive corrections, and MASD, which robustly measures a layer's average contribution. Extensive experiments on multiple models ranging from 0.5B to 13B parameters demonstrate that SimDiff significantly outperforms state-of-the-art baselines across various pruning ratios. Notably, our method retains over 91% of LLaMA2-7B's performance at a 25% pruning ratio and achieves up to a 1.49x inference speedup when pruning 12 layers on LLaMA3.1-8B. We also show that pruned models can be effectively recovered with minimal fine-tuning.

Yuli Chen, Shuhao Zhang, Fanshen Meng +4

LLM PruningLLM Inference AccelerationNeural Network Pruning
AskPDF
Apr 21, 2026cs.AI

GRASPrune: Global Gating for Budgeted Structured Pruning of Large Language Models

Large language models (LLMs) are expensive to serve because model parameters, attention computation, and KV caches impose substantial memory and latency costs. We present GRASPrune, a structured pruning framework applied after pretraining that jointly prunes FFN channels and KV head groups under a single global budget. Instead of learning importance scores without constraints and applying the budget only after training, GRASPrune learns lightweight gate scores with a projected straight-through estimator that enforces a hard mask satisfying the budget at every step while keeping the backbone weights frozen. After the mask is fixed, we calibrate scaling factors on the retained units to mitigate scale mismatch caused by pruning, and fold these factors into the pruned weights to obtain a smaller dense checkpoint with no extra parameters at inference. On LLaMA-2-7B, GRASPrune removes 50% of parameters and achieves 12.18 perplexity on WikiText-2 while maintaining competitive average zero-shot accuracy on five benchmarks, using four epochs on 512 unlabeled calibration sequences on a single NVIDIA A100 80GB GPU without any full model fine-tuning.

Ziyang Wang, Jiangfeng Xiao, Chuan Xiao +3

Beijing Institute of Technology, Zhuhai · Shenzhen University · Osaka University

LLM PruningLLM CompressionStructured Pruning
AskPDF
Apr 19, 2026cs.CL

CRISP: Compressing Redundancy in Chain-of-Thought via Intrinsic Saliency Pruning

Long Chain-of-Thought (CoT) reasoning is pivotal for the success of recent reasoning models but suffers from high computational overhead and latency. While prior works attempt to compress CoT via external compressor, they often fail to align with the model's internal reasoning dynamics, resulting in the loss of critical logical steps. This paper presents \textbf{C}ompressing \textbf{R}edundancy in Chain-of-Thought via \textbf{I}ntrinsic \textbf{S}aliency \textbf{P}runing (\textbf{CRISP}), a framework that compresses CoT by exploiting the model's intrinsic saliency. Our analysis reveals a distinct phenomenon: the reasoning termination token \texttt{[object Object]} acts as an information anchor, where its attention pattern effectively demarcates essential reasoning from redundancy. Based on this finding, we design a policy that utilizes these intrinsic attention signals to guide atomic compression operations. In contrast to coarse-grained pruning strategies, CRISP strategically distills the reasoning chain to maximize information density while preserving logical coherence. Empirical results across various backbone models and mathematical datasets demonstrate that CRISP achieves a 50-60% reduction in token count without compromising accuracy, effectively mitigating the efficiency bottleneck of long-context reasoning. We open-source our implementation to facilitate further research in efficient reasoning.

Yangsong Lan, Hongliang Dai, Piji Li

College of Artificial Intelligence, Nanjing University of Aeronautics and Astronautics, Nanjing, China · The Key Laboratory of Brain-Machine Intelligence Technology, Ministry of Education, Nanjing, China.

LLM PruningLLM CompressionLLM Inference AccelerationCoT Compression
AskPDF
Apr 18, 2026cs.CL

Prune, Interpret, Evaluate: A Cross-Layer Transcoder-Native Framework for Efficient Circuit Discovery via Feature Attribution

Existing feature-interpretation pipelines typically operate on uniformly sampled units or exhaustive feature sets, incurring massive costs on units irrelevant to target behaviors. To address this, we introduce the first CLT-native end-to-end pruning framework, PIE, which pioneers the paradigm of pruning first and interpreting later. PIE connects Pruning, automatic Interpretation, and interpretation Evaluation, establishing a comprehensive benchmarking environment to systematically measure behavioral fidelity and downstream interpretability under pruning. Within this framework, we adapt strong relevance baselines and propose Feature Attribution Patching (FAP), a patch-grounded attribution method that scores CLT features by aggregating gradient-weighted write contributions. Furthermore, we introduce FAP-Synergy, a systematic synergy-aware reranking procedure. We evaluate pruning using KL-divergence behavior retention and assess interpretation quality with FADE-style metrics across IOI and Doc-String datasets. Across budget constraints of K in {50, 100, 200, 400, 800}, our rigorous benchmarking reveals distinct operational regimes: while base FAP and adapted baselines perform robustly at relaxed budgets, FAP-Synergy excels in highly constrained, strict-budget regimes. Crucially, we demonstrate a practical "Effective Budget" advantage: on the IOI task for both Llama-3.2-1B and Gemma-2-2B, FAP-Synergy at K=50 functionally matches the behavioral fidelity of baseline circuits at K=75. Because downstream evaluation costs scale linearly per feature, Synergy effectively grants the pipeline 25 "free" features, achieving K=75 fidelity while reducing interpretation costs by 33%.

Qinhao Chen, Linyang He, Nima Mesgarani

Columbia University

LLM PruningFeature AttributionCircuit DiscoveryMechanistic InterpretabilityExplainability Evaluation
AskPDF
Apr 17, 2026cs.CL

Optimizing Korean-Centric LLMs via Token Pruning

This paper presents a systematic benchmark of state-of-the-art multilingual large language models (LLMs) adapted via token pruning - a compression technique that eliminates tokens and embedding parameters corresponding to languages irrelevant to the target application. Focusing on Korean-centric natural language processing (NLP) tasks, we evaluate architectures including Qwen3, Gemma-3, Llama-3, and Aya across three vocabulary configurations: Original, English-Korean (EnKo), and English-Korean-Chinese (EnKoZh). Performance is assessed using established benchmarks for general aptitude, cultural literacy, instruction following, and machine translation. Our findings indicate that token pruning significantly improves generation stability by eliminating language confusion, and in the case of machine translation, frequently enhances performance on Korean-specific tasks. While instruction-following capabilities display architecture-dependent variance linked to latent cross-lingual representations, the significant reduction in vocabulary size validates token pruning as a highly effective optimization strategy for memory-constrained, domain-specific deployments, despite modest gains in inference latency.

Hoyeol Kim, Hyeonwoo Kim

College of Computing · Independent Researcher

Multilingual Language Model EvaluationLLM PruningLLM CompressionLanguage Modeling
AskPDF
Apr 17, 2026cs.LG

Pruning Unsafe Tickets: A Resource-Efficient Framework for Safer and More Robust LLMs

Machine learning models are increasingly deployed in real-world applications, but even aligned models such as Mistral and LLaVA still exhibit unsafe behaviors inherited from pre-training. Current alignment methods like SFT and RLHF primarily encourage models to generate preferred responses, but do not explicitly remove the unsafe subnetworks that trigger harmful outputs. In this work, we introduce a resource-efficient pruning framework that directly identifies and removes parameters associated with unsafe behaviors while preserving model utility. Our method employs a gradient-free attribution mechanism, requiring only modest GPU resources, and generalizes across architectures and quantized variants. Empirical evaluations on ML models show substantial reductions in unsafe generations and improved robustness against jailbreak attacks, with minimal utility loss. From the perspective of the Lottery Ticket Hypothesis, our results suggest that ML models contain "unsafe tickets" responsible for harmful behaviors, and pruning reveals "safety tickets" that maintain performance while aligning outputs. This provides a lightweight, post-hoc alignment strategy suitable for deployment in resource-constrained settings.

Wai Man Si, Mingjie Li, Michael Backes +1

CISPA Helmholtz Center for Information Security

LLM PruningLLM Safety AlignmentLLM SafetyNeural Network Pruning
AskPDF
Apr 14, 2026cs.LG

MOONSHOT : A Framework for Multi-Objective Pruning of Vision and Large Language Models

Weight pruning is a common technique for compressing large neural networks. We focus on the challenging post-training one-shot setting, where a pre-trained model is compressed without any retraining. Existing one-shot pruning methods typically optimize a single objective, such as a layer-wise reconstruction loss or a second-order Taylor approximation of the training loss. We highlight that neither objective alone is consistently the most effective across architectures and sparsity levels. Motivated by this insight, we propose MOONSHOT, a general and flexible framework that extends any single-objective pruning method into a multi-objective formulation by jointly optimizing both the layer-wise reconstruction error and second-order Taylor approximation of the training loss. MOONSHOT acts as a wrapper around existing pruning algorithms. To enable this integration while maintaining scalability to billion-parameter models, we propose modeling decisions and introduce an efficient procedure for computing the inverse Hessian, preserving the efficiency of state-of-the-art one-shot pruners. When combined with state-of-the-art pruning methods on Llama-3.2 and Llama-2 models, MOONSHOT reduces C4 perplexity by up to 32.6% at 2:4 sparsity and improves zero-shot mean accuracy across seven classification benchmarks by up to 4.9 points. On Vision Transformers, it improves accuracy on ImageNet-1k by over 5 points at 70% sparsity, and on ResNet-50, it yields a 4-point gain at 90% sparsity.

Gabriel Afriat, Xiang Meng, Shibal Ibrahim +2

Operations Research Center Massachusetts Institute of Technology · Google · OpenAI +1

LLM PruningNeural Network Pruning
AskPDF
Mar 5, 2026cs.CL

Measuring the Redundancy of Decoder Layers in SpeechLLMs

Speech Large Language Models route speech encoder representations into an LLM decoder that typically accounts for over 90% of total parameters. We study how much of this decoder capacity is actually needed for speech tasks. Across two LLM families and three scales (1-8B), we show that decoder redundancy is largely inherited from the pretrained LLM: text and speech inputs yield similar redundant blocks. We then measure excess capacity by pruning decoder layers and analysing post-pruning healing to increase robustness. Our findings show that 7-8B models retain good ASR performance with only 60% of decoder layers, and the same trend extends to smaller scales with reduced pruning tolerance. We then generalise to speech translation, and show that the same blocks of layers are redundant across speech encoders, tasks and languages, indicating that a more global redundancy structure exists, enabling a single pruned and multi-tasks SpeechLLM backbone to be deployed.

Adel Moumen, Guangzhi Sun, Philip C Woodland

Department of Engineering, University of Cambridge, UK

LLM PruningTransformerAutomatic Speech RecognitionSpeech Language Models
AskPDF
Mar 1, 2026cs.IT

Curvature-Weighted Capacity Allocation: A Minimum Description Length Framework for Layer-Adaptive Large Language Model Optimization

Layer-wise capacity in large language models is highly non-uniform: some layers contribute disproportionately to loss reduction, whereas others are nearly redundant. Existing layer-scoring methods provide sensitivity estimates but do not give a principled rule for converting those estimates into allocation or pruning decisions under a global hardware budget. We introduce a curvature-aware, MDL-inspired framework built around the layer gain ζk2=gk⊤H~kk−1gkζ_k^2=g_k^\top\widetilde H_{kk}^{-1}g_k. This quantity equals twice the maximal decrease predicted by the regularized layer-restricted quadratic model and incorporates inverse local curvature; it is therefore a local surrogate for reducible risk, not a universal dominance claim over gradient-norm scores. After normalizing the gains into scores qkq_k, we formulate two convex programs: one allocates expert slots under diminishing returns, and the other assigns layer-wise pruning ratios while protecting high-score layers. Both continuous programs have unique globally optimal solutions characterized by one dual variable and computable in O(Klog⁡(1/ε))O(K\log(1/\varepsilon)) time by bisection. We also prove a quadratic transfer-regret bound: when source and target score vectors differ by at most δδ, the target surrogate cost of the transferred decision is within O(δ2)O(δ^2) of the target optimum. Experiments on Mistral-7B and Gemma-7B show clear allocation gains in some settings and competitive, though mixed, pruning performance. The framework therefore replaces an empirical score-to-decision heuristic with a budget-feasible optimization procedure whose guarantees apply to the stated continuous surrogates. Code is available on github repo - TKAI-LAB-Mali/Curvature-Weighted-Capacity-Allocation

Theophilus Amaefuna, Hitesh Vaidya, Anshuman Chhabra +1

1Bellini College of Artificial Intelligence, Cybersecurity and Computing University of South Florida, Tampa, Florida, USA

LLM PruningLLM Compression
AskPDF
Jan 11, 2026cs.CL

Garbage Attention in Large Language Models: BOS Sink Heads and Sink-aware Pruning

Large Language Models (LLMs) are known to contain significant redundancy, yet a systematic explanation for why certain components, particularly in higher layers, are more redundant has remained elusive. In this work, we identify the BOS sink phenomenon as a key mechanism driving this layer-wise sensitivity. We show that attention heads with high BOS sink scores are strongly associated with functional redundancy: such heads, especially in deeper layers, contribute little to predictive performance and effectively serve as dumping grounds for superfluous attention weights. Leveraging this insight, we introduce a simple pruning strategy that removes high-BOS sink heads. Experiments on Gemma-3, Llama-3.1, and Qwen3 demonstrate that this approach identifies redundant transformer components more reliably than weight- and activation-based criteria in terms of downstream task retention, remaining close to dense baselines at low-to-moderate pruning ratios. We further find that high-scoring sink heads sustain their focus on BOS as context length grows. Overall, our results suggest that structural properties of attention offer a more direct basis for model compression than magnitude-based methods.

Jaewon Sok, Jewon Yeom, Seonghyeon Park +2

Department of Rural Systems Engineering, Seoul National University · Graduate School of Data Science, Seoul National University · Department of Aerospace Engineering, Seoul National University

LLM PruningAttention Head AnalysisSelf-AttentionTransformer AttentionAttention SinksAttention Mechanisms+2
AskPDF
Dec 3, 2025cs.LG

Data-Free Pruning of Self-Attention Layers in LLMs

Many self-attention sublayers in large language models (LLMs) can be removed with little to no loss. We attribute this to the Attention Suppression Hypothesis: during pre-training, some deep attention layers learn to mute their own contribution, leaving the residual stream and the MLP to carry the representation. We propose Gate-Norm, a one-shot, weight-only criterion that ranks attention sublayers by query-key coupling and removes the least coupled ones, requiring no calibration data, no forward passes, no fine-tuning, and no specialized kernels. On 40-layer, 13B-parameter LLaMA models, Gate-Norm prunes the model in under a second. Pruning 8-16 attention sublayers yields up to 1.30×1.30\times higher inference throughput while keeping average zero-shot accuracy within 1.5 percentage points of the unpruned baseline across BoolQ, RTE, HellaSwag, WinoGrande, ARC-Easy/Challenge, and OpenBookQA. Across these settings, Gate-Norm matches data-driven pruning methods in accuracy while being ∼1000×\sim 1000\times faster to score layers, enabling practical, data-free compression of LLMs.

Dhananjay Saikumar, Blesson Varghese

School of Computer Science University of St Andrews United Kingdom

LLM PruningLLM CompressionSelf-AttentionLLM Inference AccelerationAttention MechanismsNeural Network Pruning
AskPDF
Sep 27, 2025cs.LG

PATCH: Learnable Tile-level Hybrid Sparsity for LLMs

Large language models (LLMs) deliver impressive performance but incur prohibitive memory and compute costs at deployment. Model pruning is an effective way to reduce these overheads, yet existing approaches face challenges: unstructured sparsity, where nonzeros can appear anywhere, preserves accuracy but yields irregular access patterns that prevent GPU acceleration, while semi-structured 2:4 sparsity is hardware-friendly but enforces a rigid 50% pattern that degrades model quality. To bridge this gap, we introduce PATCH, a hybrid sparsity framework that enables a continuous sparsity ratio between 0% and 50%. PATCH partitions weight matrices into tiles, assigning each tile to be either dense or 2:4 sparse via a learnable mask selection mechanism. This design provides fine-grained control over accuracy-acceleration tradeoffs and supports non-uniform sparsity across layers, leading to superior overall quality. Across models from 0.5B to 13B parameters, PATCH consistently narrows the gap to dense accuracy while delivering practical speedups. For instance, on LLaMA-2 7B with an A6000 GPU, PATCH achieves 1.18x-1.38x end-to-end speedup over dense baselines while improving accuracy by 0.37%-2.96% compared to the state-of-the-art 2:4 pruning method, MaskLLM.

Younes Hourri, Mohammad Mozaffari, Maryam Mehri Dehnavi

Department of Computer Science University of Toronto

LLM PruningLLM CompressionStructured SparsityLLM Inference AccelerationNeural Network Pruning
AskPDF
May 19, 2025cs.CL

A Token is Worth over 1,000 Tokens: Efficient Knowledge Distillation through Low-Rank Clone

Training high-performing Small Language Models (SLMs) remains costly, even with knowledge distillation and pruning from larger teacher models. Existing work often faces three key challenges: (1) information loss from hard pruning, (2) inefficient alignment of representations, and (3) underutilization of informative activations, particularly from Feed-Forward Networks (FFNs). To address these challenges, we introduce Low-Rank Clone (LRC), an efficient pre-training method that constructs SLMs aspiring to behavioral equivalence with strong teacher models. LRC trains a set of low-rank projection matrices that jointly enable soft pruning by compressing teacher weights, and activation clone by aligning student activations, including FFN signals, with those of the teacher. This unified design maximizes knowledge transfer while removing the need for explicit alignment modules. Extensive experiments with open-source teachers (e.g., Llama-3.2-3B-Instruct, Qwen2.5-3B/7B-Instruct) show that LRC matches or surpasses state-of-the-art models trained on trillions of tokens--while using only 20B tokens, achieving over 1,000x training efficiency. Our codes and model checkpoints are available at https://github.com/CURRENTF/LowRankClone and https://huggingface.co/collections/JitaiHao/low-rank-clone-lrc-6828389e96a93f1d4219dfaf.

Jitai Hao, Qiang Huang, Hao Liu +3

School of Intelligence Science and Engineering, Harbin Institute of Technology, Shenzhen · Baidu Inc. · Leiden University +1

Language Model PretrainingLLM PruningLLM CompressionSmall Language ModelsLanguage Model DistillationKnowledge Distillation
AskPDF
May 13, 2025cs.CL

Adaptive GoGI-Skip: Coupling Goal-Gradient Importance with Dynamic Uncertainty for Efficient Reasoning

Chain-of-Thought (CoT) prompting trades inference speed for reasoning accuracy. Existing compressors force a compromise as static gradient techniques treat tokens independently, severing sequential logic, while uncertainty-based pruning ignores the final answer. We introduce Adaptive GoGI-Skip, a framework that resolves this tension by non-linearly coupling Goal-Gradient Importance (GoGI) with Adaptive Dynamic Skipping (ADS). GoGI quantifies each token's functional contribution to answer correctness via gradient sensitivity. ADS leverages runtime entropy to dynamically modulate the GoGI threshold, preserving low-gradient tokens essential for structural coherence at high-uncertainty junctions. Trained on 7,472 MATH traces, our policy transfers zero-shot to AIME, GPQA, and GSM8K, reducing token volume by >>45% and accelerating inference up to 2.0×\times without accuracy loss. These results suggest that thinking-optimal compression demands synergy between teleological goals and epistemic uncertainty.

Ren Zhuang

School of Information Science and Technology, Hangzhou Normal University

Gradient-Based AttributionLLM PruningLLM Inference AccelerationEfficient Language Model InferenceCoT Compression
AskPDF
Feb 11, 2025cs.LG

DarwinLM: Evolutionary Structured Pruning of Large Language Models

Large Language Models (LLMs) have achieved significant success across various NLP tasks. However, their massive computational costs limit their widespread use, particularly in real-time applications. Structured pruning offers an effective solution by compressing models and directly providing end-to-end speed improvements, regardless of the hardware environment. Meanwhile, different components of the model exhibit varying sensitivities towards pruning, calling for non-uniform model compression. However, a pruning method should not only identify a capable substructure, but also account for post-compression training. To this end, we propose DarwinLM, a method for training-aware structured pruning. DarwinLM builds upon an evolutionary search process, generating multiple offspring models in each generation through mutation, and selecting the fittest for survival. To assess the effect of post-training, we incorporate a lightweight, multistep training process within the offspring population, progressively increasing the number of tokens and eliminating poorly performing models in each selection stage. We validate our method through extensive experiments on Llama-2-7B, Llama-3.1-8B and Qwen-2.5-14B-Instruct, achieving state-of-the-art performance for structured pruning. For instance, DarwinLM surpasses ShearedLlama while requiring 5x less training data during post-compression training. Code is at: https://github.com/IST-DASLab/DarwinLM

Shengkun Tang, Oliver Sieberling, Eldar Kurtic +2

MBZUAI · ETH Zurich · ISTA +1

LLM PruningStructured Pruning
AskPDF
Date pendingcs.LG

LLM Compression by Block Removal with Constrained Binary Optimization

In this paper, we formulate the compression of large language models (LLMs) by optimally deleting transformer blocks (``block removal'') as a constrained binary optimization (CBO) problem that can be mapped to a physical system (Ising glass), whose energies are a strong proxy for downstream model performance. This formulation enables an efficient ranking of a large number of candidate block-removal configurations yielding many high-quality, non-trivial solutions beyond those only removing consecutive regions. Our method performs strongly in the deep compression regime, such as for 50% compression of Llama-3.3-70B-Instruct, where we achieve an almost 23 percentage point increase on the MMLU benchmark compared to other state-of-the-art (SOTA) block-removal methods. For lighter compression, it performs on par with those methods across several benchmarks for Llama-3.1-8B-Instruct, Qwen3-14B (both before and after retraining), as well as Llama-3.3-70B-Instruct. The approach is computationally efficient and requires only forward and backward passes on a calibration dataset for a few active parameters. Additionally, we demonstrate that using good heuristic solvers for the CBO problem provides solutions that perform well on downstream tasks in negligible runtime when it is unfeasible to solve the problem exactly. The method can be readily applied to any architecture. We illustrate this generality on the recent NVIDIA-Nemotron-3-Nano-30B-A3B-FP8 model, which exhibits a highly inhomogeneous and challenging block structure, and where we outperform SOTA for AIME25 and GPQA when removing either 2 attention layers or 3 mixture-of-experts layers.

David Jansen, Roman Rausch, Ali Hashemi +2

Multiverse Computing · Donostia International Physics Center Ikerbasque Foundation for Science

LLM PruningLLM CompressionNeural Network Pruning
AskPDF