arXiv AI June 3, 2026 By Hu Xu, Zhaolong Xing, Congcong Liu, Jiaxing Wang, Zhida Jiang, Junshi Huang, Zhen Chen, Jianfeng Xu

Calibration Data Trade-offs Across Capability Dimensions: Why Multi-Source Mixing Matters for High-Sparsity LLM Pruning

Read the original on arXiv AI →

arXiv:2606. 03328v1 Announce Type: cross Abstract: Post-training pruning compresses large language models to high sparsity using a small unlabelled calibration set, and recent work has concluded that the choice of calibration source has only modest impact on averaged post-pruning accuracy.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv Machine Learning

Jul 31

Averaged Evaluation Masks Capability Trade-Offs: Multi-Source Calibration for High-Sparsity LLM Pruning

arXiv:2606. 03328v3 Announce Type: replace Abstract: Calibration data are often treated as a minor implementation detail in post-training LLM pruning because averaged evaluations suggest only modest effects.

By Hu Xu, Zhaolong Xing, Congcong Liu, Jiaxing Wang, Zhida Jiang, Junshi Huang, Zhen Chen, Jianfeng Xu

llms efficiency

arXiv AI

Jun 29

Output-Space Allocation Costs for Calibration-Guided LLM Compression: An Empirical Study

arXiv:2606. 27785v1 Announce Type: cross Abstract: Training-free compression methods for large language models (LLMs) often use calibration data to guide compression decisions.

By Qiong Tang, Xiangkun Hu, Xiangyang Liu, Yiran Chen, Yunfan Shao

llms benchmarks

arXiv Machine Learning

Jun 17

AIMER: Calibration-Free Task-Agnostic MoE Expert Pruning

arXiv:2603. 18492v3 Announce Type: replace Abstract: Mixture-of-Experts (MoE) language models increase parameter capacity without proportional per-token computation, yet deployment still requires storing the full expert pool, making expert pruning important for reducing memory and serving overhead.

By Zongfang Liu, Guangyi Chen, Shengkun Tang, Yifan Shen, Huan Wang, Xin Yuan

llms efficiency benchmarks

arXiv AI

Jul 3

Generic Expert Coverage for Pruning SparseMixture-of-Experts Language Models

arXiv:2607. 01710v1 Announce Type: new Abstract: Sparsely activated Mixture-of-Experts (MoE) language models contain substantial structured redundancy among routed experts, but pruning them without downstream calibration data remains challenging.

By Yongqin Zeng, Sicheng Pan, Jiale Wang, Hai-tao Zheng, Hong-Gee Kim, Chunxia Ma, XiuTeng Zhou

llms efficiency benchmarks safety

arXiv AI

Jul 22

CompilerKV: Risk-Adaptive KV Compression via Offline Experience Compilation

arXiv:2602. 08686v3 Announce Type: replace-cross Abstract: Prefill-only KV compression freezes a token subset at the end of prefill and decodes from it without further eviction.

By Ning Yang, Chengzhi Wang, Yibo Liu, Baoliang Tian, Haijun Zhang

benchmarks

arXiv Machine Learning

1d ago

Certifying Compressed Language Models: An Audit and a Statistical Toolkit

arXiv:2608. 15046v1 Announce Type: new Abstract: A fraction of a point of benchmark accuracy is the usual evidence that a compressed model is equivalent to its original.

By Amogh Singh

llms benchmarks

Related stories

Averaged Evaluation Masks Capability Trade-Offs: Multi-Source Calibration for High-Sparsity LLM Pruning

Output-Space Allocation Costs for Calibration-Guided LLM Compression: An Empirical Study

AIMER: Calibration-Free Task-Agnostic MoE Expert Pruning

Generic Expert Coverage for Pruning SparseMixture-of-Experts Language Models

CompilerKV: Risk-Adaptive KV Compression via Offline Experience Compilation

Certifying Compressed Language Models: An Audit and a Statistical Toolkit