Paper Citation Record · LEDGER

Lightweight and Post-Training Structured Pruning for On-Device Large Lanaguage Models

As of 11 August 2026, this Paper Citation Record lists 47 of 47 outbound references and 0 inbound Pith citation observations for arXiv:2501.15255.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2501.15255 v1

Coverage vector

measured 47 of 47 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-10T14:33:44.492537Z

measured 47 of 47 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-11T06:34:44.6726+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: cited_works

Reference resolution

47 of 47 outbound references displayed

verified exact0
verified fuzzy18
unresolved29
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 013c793a-1f4f-44fd-b559-a65f588a533b · outbound

This paper cites A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systems.

Lightweight and Post-Training Structured Pruning for On-Device Large Lanaguage Models A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systems

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-10T14:33:44.336597Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 860e4a02-c02c-4311-8f6f-44a309285257 · outbound

This paper cites Toolqa: A dataset for llm question answering with external tools,.

Lightweight and Post-Training Structured Pruning for On-Device Large Lanaguage Models Toolqa: A dataset for llm question answering with external tools,

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-10T14:33:44.341216Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1fc67cd9-391c-468d-bbff-7aea2db876af · outbound

This paper cites A comprehensive survey on process-oriented automatic text summarization with exploration of llm-based methods,.

Lightweight and Post-Training Structured Pruning for On-Device Large Lanaguage Models A comprehensive survey on process-oriented automatic text summarization with exploration of llm-based methods,

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-10T14:33:44.345007Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03eb5be2-6622-44c8-a793-b71cffa218ee · outbound

This paper cites Exploding ai power use: an opportunity to rethink grid planning and management,.

Lightweight and Post-Training Structured Pruning for On-Device Large Lanaguage Models Exploding ai power use: an opportunity to rethink grid planning and management,

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:33:44.984078Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 87360897-f9a6-44b5-98b5-7ba475a0e4a4 · outbound

This paper cites Carbon Emissions and Large Neural Network Training.

Lightweight and Post-Training Structured Pruning for On-Device Large Lanaguage Models Carbon Emissions and Large Neural Network Training

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-10T14:33:44.352118Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0878c019-51b2-461a-a433-a919b5d8c977 · outbound

This paper cites Drive as you speak: Enabling human-like interaction with large language models in au- tonomous vehicles,.

Lightweight and Post-Training Structured Pruning for On-Device Large Lanaguage Models Drive as you speak: Enabling human-like interaction with large language models in au- tonomous vehicles,

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-10T14:33:44.355940Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77454a21-ecf1-4483-8279-175eee468d69 · outbound

This paper cites LLM as a System Service on Mobile Devices.

Lightweight and Post-Training Structured Pruning for On-Device Large Lanaguage Models LLM as a System Service on Mobile Devices

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-10T14:33:44.359780Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 457735b4-acc0-4490-934d-fb2fc19db4b8 · outbound

This paper cites Language models are few-shot learners advances,.

Lightweight and Post-Training Structured Pruning for On-Device Large Lanaguage Models Language models are few-shot learners advances,

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:33:44.969294Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation a448f3cd-607c-401b-b630-272fa0a7df22 · outbound

This paper cites Energy and policy consid- erations for modern deep learning research,.

Lightweight and Post-Training Structured Pruning for On-Device Large Lanaguage Models Energy and policy consid- erations for modern deep learning research,

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:33:44.959998Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation bfda8e4c-9cf8-440c-a99f-ef35692fcf58 · outbound

This paper cites Learning both weights and connections for efficient neural network,.

Lightweight and Post-Training Structured Pruning for On-Device Large Lanaguage Models Learning both weights and connections for efficient neural network,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-10T14:33:44.370200Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3d97847-33d0-4074-bebf-99c305448449 · outbound

This paper cites The lottery ticket hypothesis: Finding sparse, trainable neural networks,.

Lightweight and Post-Training Structured Pruning for On-Device Large Lanaguage Models The lottery ticket hypothesis: Finding sparse, trainable neural networks,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-10T14:33:44.374805Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41187ac8-a6c5-4cda-8770-24186917364d · outbound

This paper cites Stabilizing the Lottery Ticket Hypothesis.

Lightweight and Post-Training Structured Pruning for On-Device Large Lanaguage Models Stabilizing the Lottery Ticket Hypothesis

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-10T14:33:44.378653Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c848a58c-8bad-4138-84a1-1b8e3aad5b48 · outbound

This paper cites Sparsegpt: Massive language models can be accurately pruned in one-shot,.

Lightweight and Post-Training Structured Pruning for On-Device Large Lanaguage Models Sparsegpt: Massive language models can be accurately pruned in one-shot,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-10T14:33:44.382403Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8778de6-39f8-4a3b-8b69-eb9b73f8b73d · outbound

This paper cites Plug-and-play: An efficient post-training pruning method for large language models,.

Lightweight and Post-Training Structured Pruning for On-Device Large Lanaguage Models Plug-and-play: An efficient post-training pruning method for large language models,

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:33:44.931726Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 861098ea-9bf3-4585-864d-f04b67e44447 · outbound

This paper cites Nvidia a100 tensor core gpu: Performance and innovation,.

Lightweight and Post-Training Structured Pruning for On-Device Large Lanaguage Models Nvidia a100 tensor core gpu: Performance and innovation,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-10T14:33:44.389083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c15ccb1a-c0a3-4875-bd00-d852470f5f1a · outbound

This paper cites A fast post-training pruning framework for transformers,.

Lightweight and Post-Training Structured Pruning for On-Device Large Lanaguage Models A fast post-training pruning framework for transformers,

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:33:44.915181Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 6025b344-80c9-4c59-be53-413b5e2085df · outbound

This paper cites Loraprune: Structured pruning meets low-rank parameter-efficient fine- tuning,.

Lightweight and Post-Training Structured Pruning for On-Device Large Lanaguage Models Loraprune: Structured pruning meets low-rank parameter-efficient fine- tuning,

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:33:44.905108Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 914996d1-6d6c-4f73-a1a2-336f930a7cdf · outbound

This paper cites ShortGPT: Layers in Large Language Models are More Redundant Than You Expect.

Lightweight and Post-Training Structured Pruning for On-Device Large Lanaguage Models ShortGPT: Layers in Large Language Models are More Redundant Than You Expect

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-10T14:33:44.399302Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18d08712-db2b-468a-b654-b6af2fede839 · outbound

This paper cites Llm-pruner: On the structural pruning of large language models,.

Lightweight and Post-Training Structured Pruning for On-Device Large Lanaguage Models Llm-pruner: On the structural pruning of large language models,

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:33:44.894912Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 32b8e711-9b39-4c5d-84cb-5a62ec94e6f7 · outbound

This paper cites A Simple and Effective Pruning Approach for Large Language Models.

Lightweight and Post-Training Structured Pruning for On-Device Large Lanaguage Models A Simple and Effective Pruning Approach for Large Language Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-10T14:33:44.407072Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2148dfb3-c847-4963-a91b-e4028f9fdb03 · outbound

This paper cites Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey.

Lightweight and Post-Training Structured Pruning for On-Device Large Lanaguage Models Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-10T14:33:44.410576Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 86fc1f16-90c8-40af-ae3e-61c118806114 · outbound

This paper cites LoRA: Low-Rank Adaptation of Large Language Models.

Lightweight and Post-Training Structured Pruning for On-Device Large Lanaguage Models LoRA: Low-Rank Adaptation of Large Language Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-10T14:33:44.414119Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bbf3125e-d4a0-4f6e-8220-2a763776e682 · outbound

This paper cites Compacter: Efficient low-rank hypercomplex adapter layers,.

Lightweight and Post-Training Structured Pruning for On-Device Large Lanaguage Models Compacter: Efficient low-rank hypercomplex adapter layers,

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-10T14:33:44.417177Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b82c9b1a-9d5c-46f2-9a02-ef2cf2de04d0 · outbound

This paper cites Decoupled weight decay regularization,.

Lightweight and Post-Training Structured Pruning for On-Device Large Lanaguage Models Decoupled weight decay regularization,

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-10T14:33:44.419846Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 004b8d87-4e38-425d-badd-3ebb660de9b6 · outbound

This paper cites Privacy-preserving large language models for structured medical information retrieval,.

Lightweight and Post-Training Structured Pruning for On-Device Large Lanaguage Models Privacy-preserving large language models for structured medical information retrieval,

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:33:44.872785Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 569f2be8-04f6-47c1-9a15-1184ec144354 · outbound

This paper cites Optimizing llm training for financial services: Best practices for model accuracy, risk management, and compliance in ai-powered financial applications,.

Lightweight and Post-Training Structured Pruning for On-Device Large Lanaguage Models Optimizing llm training for financial services: Best practices for model accuracy, risk management, and compliance in ai-powered financial applications,

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:33:44.862571Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 413ef0f4-ae05-4b25-8b63-c54a62aa4674 · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

Lightweight and Post-Training Structured Pruning for On-Device Large Lanaguage Models Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-10T14:33:44.431221Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56a01d3e-b6ad-44d5-b313-0840ed563c95 · outbound

This paper cites SliceGPT: Compress Large Language Models by Deleting Rows and Columns.

Lightweight and Post-Training Structured Pruning for On-Device Large Lanaguage Models SliceGPT: Compress Large Language Models by Deleting Rows and Columns

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-10T14:33:44.434000Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6853423-0452-43d1-8d62-1c0be72bec33 · outbound

This paper cites Deja vu: Contextual sparsity for efficient llms at inference time,.

Lightweight and Post-Training Structured Pruning for On-Device Large Lanaguage Models Deja vu: Contextual sparsity for efficient llms at inference time,

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:33:44.852104Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation fac87cdc-d51f-4666-9662-c5f8cee278ec · outbound

This paper cites Bert: Pre-training of deep bidirectional transformers for language understanding,.

Lightweight and Post-Training Structured Pruning for On-Device Large Lanaguage Models Bert: Pre-training of deep bidirectional transformers for language understanding,

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-10T14:33:44.439465Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8cf8064d-e626-43a5-adb0-c58efa3558ba · outbound

This paper cites An estimate for the condition number of a matrix,.

Lightweight and Post-Training Structured Pruning for On-Device Large Lanaguage Models An estimate for the condition number of a matrix,

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:33:44.835773Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 0c50f56f-9e78-4011-9f98-3db1ae1fbb79 · outbound

This paper cites Matrix inversion using cholesky decomposition,.

Lightweight and Post-Training Structured Pruning for On-Device Large Lanaguage Models Matrix inversion using cholesky decomposition,

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:33:44.825043Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 68e0d6a8-843e-49f8-9223-ddacac42845c · outbound

This paper cites Points of significance: model selection and overfitting,.

Lightweight and Post-Training Structured Pruning for On-Device Large Lanaguage Models Points of significance: model selection and overfitting,

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:33:44.814768Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 436bbed2-b290-45c9-8d32-a2f722798a0b · outbound

This paper cites OPT: Open Pre-trained Transformer Language Models.

Lightweight and Post-Training Structured Pruning for On-Device Large Lanaguage Models OPT: Open Pre-trained Transformer Language Models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-10T14:33:44.452010Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97024a3e-4502-4863-88e1-91012bdd692b · outbound

This paper cites GLM-130B: An Open Bilingual Pre-trained Model.

Lightweight and Post-Training Structured Pruning for On-Device Large Lanaguage Models GLM-130B: An Open Bilingual Pre-trained Model

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-10T14:33:44.455177Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f4493f7-b8f6-4015-9178-4a4f842e31f3 · outbound

This paper cites Pointer Sentinel Mixture Models.

Lightweight and Post-Training Structured Pruning for On-Device Large Lanaguage Models Pointer Sentinel Mixture Models

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-10T14:33:44.458701Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 39a0375b-ff2f-4ce5-a68c-f04d50aaa29e · outbound

This paper cites Building a large annotated corpus of english: The penn treebank,.

Lightweight and Post-Training Structured Pruning for On-Device Large Lanaguage Models Building a large annotated corpus of english: The penn treebank,

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-10T14:33:44.461865Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 211e2d4c-1762-437e-9d0f-0cec7d247e90 · outbound

This paper cites Compressing pre-trained language models by matrix decomposition,.

Lightweight and Post-Training Structured Pruning for On-Device Large Lanaguage Models Compressing pre-trained language models by matrix decomposition,

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:33:44.797749Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 20dbe893-cd7c-414e-98a3-8e24a909e03c · outbound

This paper cites BoolQ: Exploring the surprising difficulty of natural yes/no questions,.

Lightweight and Post-Training Structured Pruning for On-Device Large Lanaguage Models BoolQ: Exploring the surprising difficulty of natural yes/no questions,

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:33:44.786814Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 7650a08c-734f-424c-8a36-a0d5f2b19c17 · outbound

This paper cites Winogrande: An adversarial winograd schema challenge at scale,.

Lightweight and Post-Training Structured Pruning for On-Device Large Lanaguage Models Winogrande: An adversarial winograd schema challenge at scale,

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:33:44.777134Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation a5ae07b3-7fb5-4ebf-b463-0d0b87105b95 · outbound

This paper cites LogiQA: A Challenge Dataset for Machine Reading Comprehension with Logical Reasoning.

Lightweight and Post-Training Structured Pruning for On-Device Large Lanaguage Models LogiQA: A Challenge Dataset for Machine Reading Comprehension with Logical Reasoning

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-10T14:33:44.474924Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99c1038a-3f7b-406e-9e92-c72e68c59647 · outbound

This paper cites Measuring Massive Multitask Language Understanding.

Lightweight and Post-Training Structured Pruning for On-Device Large Lanaguage Models Measuring Massive Multitask Language Understanding

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-10T14:33:44.478804Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0cdf96ac-8bf5-4b8e-8641-89b058676f1a · outbound

This paper cites Piqa: Reasoning about physical commonsense in natural language,.

Lightweight and Post-Training Structured Pruning for On-Device Large Lanaguage Models Piqa: Reasoning about physical commonsense in natural language,

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:33:44.766624Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation bf75d910-6fa0-4d25-a020-fc547f3e71be · outbound

This paper cites Crowdsourcing Multiple Choice Science Questions.

Lightweight and Post-Training Structured Pruning for On-Device Large Lanaguage Models Crowdsourcing Multiple Choice Science Questions

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-10T14:33:44.485758Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8a4af68-ef6c-49b0-8545-e136c391e98b · outbound

This paper cites Exploring the limits of transfer learning with a unified text-to-text transformer,.

Lightweight and Post-Training Structured Pruning for On-Device Large Lanaguage Models Exploring the limits of transfer learning with a unified text-to-text transformer,

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-10T14:33:44.489292Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2509998-5f88-4a5f-b63c-20e94b791b83 · outbound

This paper cites Cupy: A numpy-compatible library for nvidia gpu calculations,.

Lightweight and Post-Training Structured Pruning for On-Device Large Lanaguage Models Cupy: A numpy-compatible library for nvidia gpu calculations,

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:33:44.749821Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation e4d836dd-cb1c-4e10-a6a2-522a50cae2bd · outbound

This paper cites Decoupled Weight Decay Regularization.

Lightweight and Post-Training Structured Pruning for On-Device Large Lanaguage Models Decoupled Weight Decay Regularization

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-10T14:33:44.422738Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.