Pith. sign in

REVIEW 9 cited by

DarwinLM: Evolutionary Structured Pruning of Large Language Models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2502.07780 v4 pith:OMHV5D2B submitted 2025-02-11 cs.LG cs.CL

DarwinLM: Evolutionary Structured Pruning of Large Language Models

classification cs.LG cs.CL
keywords pruningdarwinlmmodelsstructuredtrainingmethodevolutionaryhowever
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

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

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 9 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. From Layers to Submodules: Rethinking Granularity in Replacement-Based LLM Compression

    cs.CL 2026-06 unverdicted novelty 7.0

    SubFit enables better LLM compression by fitting residual bypasses to non-contiguously selected submodules, outperforming layer-granularity baselines in accuracy-perplexity trade-offs at 12.5-37.5% sparsity.

  2. Rethinking Layer Redundancy in Large Language Models: Calibration Objectives and Search for Depth Pruning

    cs.LG 2026-04 unverdicted novelty 7.0

    Calibration objectives influence redundant layer identification in LLM depth pruning more than search algorithms do, with different objectives producing different layer rankings.

  3. EvoESAP: Non-Uniform Expert Pruning for Sparse MoE

    cs.LG 2026-03 conditional novelty 7.0

    EvoESAP uses evolutionary search guided by a speculative-decoding-inspired ESAP metric to discover non-uniform layer-wise sparsity allocations for MoE expert pruning, improving generation accuracy up to 19.6% at 50% sparsity.

  4. SlimQwen: Exploring the Pruning and Distillation in Large MoE Model Pre-training

    cs.LG 2026-05 unverdicted novelty 6.0

    Pruning pretrained MoE models outperforms training from scratch, different compression methods converge after continued pretraining, and combining KD with language modeling loss plus progressive schedules yields a com...

  5. Rethinking Layer Redundancy in Large Language Models: Calibration Objectives and Search for Depth Pruning

    cs.LG 2026-04 unverdicted novelty 6.0

    Different calibration objectives produce distinct layer pruning patterns in LLMs, while search algorithms converge to similar solutions under a fixed objective.

  6. Train Large, Deploy Compact: Structured Compression for Compact Low-Rank Adaptation

    cs.LG 2025-09 conditional novelty 6.0

    PrunedLoRA tunes large-rank LoRA adapters and progressively structurally prunes A and B to a target low rank, empirically closing much of the LoRA-to-full-fine-tuning gap.

  7. TAPIOCA: Why Task- Aware Pruning Improves OOD model Capability

    cs.LG 2026-05 unverdicted novelty 5.0

    Task-aware pruning improves OOD performance by removing layers that distort task-adapted representation profiles, realigning OOD inputs with the geometry observed on ID data.

  8. TAPIOCA: Why Task- Aware Pruning Improves OOD model Capability

    cs.LG 2026-05 unverdicted novelty 5.0

    Task-aware pruning improves OOD model performance by realigning distorted OOD layerwise norm and pairwise-distance profiles with the task-adapted geometry observed on ID inputs.

  9. SlimQwen: Exploring the Pruning and Distillation in Large MoE Model Pre-training

    cs.LG 2026-05 unverdicted novelty 5.0

    Pruning pretrained MoE models outperforms training from scratch under fixed budget, different expert compression methods converge after continued training, and progressive pruning plus multi-token KD improves the fina...