论文研究
arxiv.org ·
智能家居中剪枝会破坏什么，以及何时发生？在不同架构和任务复杂度下评估大语言模型退化
该论文系统研究剪枝对智能家居工具调用能力的影响，覆盖 dense Transformer、dense hybrid 和 MoE 四类模型，以及深度、宽度、混合和专家剪枝方法。经剪枝后监督微调，在三个智能家居数据集上评估超过 19,500 个实例，并从动作组件（操作、设备、参数、取值）和任务复杂度两个维度刻画退化。结果显示：dense 模型安全剪枝区间窄、随后急剧退化，MoE 模型可承受更大剪枝幅度；剪枝先损害 grounded specificity，再影响 schema 级意图，激进剪枝可引发系统性过度拒答。作者指出选择剪枝模型用于可靠工具执行时，不应只看聚合准确率。
AI推荐理由 arXiv 新提交论文，研究剪枝对 LLM 上下文工具调用能力的影响，覆盖 4 个模型（dense Transformer、dense hybrid、MoE）和深度/宽度/混合/专家剪枝方法，在 3 个智能家居数据集上评估超过 19,500 个实例。具体新信息：dense 模型安全剪枝区间窄、退化陡峭，MoE 容忍度更高；剪枝先破坏 grounded specificity 再破坏 schema 级意图，激进剪枝可导致系统性过度拒答。对部署剪枝模型做可靠工具执行有直接参考价值，但仅限智能家居工具调用场景，结论外推需谨慎。
72
正文
Computer Science > Computation and Language
arXiv:2609.17515 (cs)
[Submitted on 15 Sep 2026]
Title:What Breaks Under Pruning in Smart Homes, and When? Evaluating LLM Degradation Across Architectures and Task Complexity
Authors:Congjing Zhang, Vashishtha Patil, Henning Lange, Usman Aleem
View a PDF of the paper titled What Breaks Under Pruning in Smart Homes, and When? Evaluating LLM Degradation Across Architectures and Task Complexity, by Congjing Zhang and 3 other authors
View PDF
HTML (experimental)
Abstract:Pruning can reduce the deployment cost of large language models (LLMs), but its impact on context-grounded tool calling remains poorly understood. We systematically study pruning-induced degradation in smart-home tool calling across four LLMs spanning dense Transformer, dense hybrid, and mixture-of-experts (MoE) architectures, together with depth, width, hybrid, and expert pruning methods. After post-pruning supervised fine-tuning (SFT), we evaluate more than 19,500 instances from three smart-home datasets. Beyond aggregate task accuracy, we characterize degradation along two dimensions: action components (i.e., operation, device, argument, and value) and task complexity. Our results show that dense models have narrow safe pruning regions followed by sharp degradation, while MoE models tolerate substantially more pruning. Pruning degrades grounded specificity before schema-level intent, and aggressive dense pruning can induce systematic over-refusal. These findings highlight the importance of evaluating pruning beyond aggregate accuracy when selecting pruned LLMs for reliable tool execution.
Comments:
Subjects:
Computation and Language (cs.CL)
Cite as:
arXiv:2609.17515 [cs.CL]
(or
arXiv:2609.17515v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2609.17515
Focus to learn more
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Congjing Zhang [view email]
[v1]
Tue, 15 Sep 2026 17:51:48 UTC (1,610 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled What Breaks Under Pruning in Smart Homes, and When? Evaluating LLM Degradation Across Architectures and Task Complexity, by Congjing Zhang and 3 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.CL
new
|
recent
| 2026-09
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)