Paper Citation Record · LEDGER

Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs

As of 4 August 2026, this Paper Citation Record lists 36 of 36 outbound references and 2 inbound Pith citation observations for arXiv:2509.25414.

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

pith.paper-citation-record.v1
2509.25414 v2

Coverage vector

measured 36 of 36 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-18T11:58:39.003926Z

measured 38 of 38 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-04T06:34:03.388597+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-03T03:49:39.658872Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

36 of 36 outbound references displayed

verified exact18
verified fuzzy15
unresolved2
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 285f5767-5067-4993-89cc-5c0b8b10225f · outbound

This paper cites GPT-4 Technical Report.

Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs GPT-4 Technical Report

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-05-18T12:01:21.188459Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 237b4d15-59a0-4a4f-9670-19daf03d3532 · outbound

This paper cites SAMO: A Lightweight Sharpness-Aware Approach for Multi-Task Optimization with Joint Global-Local Perturbation.

Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs SAMO: A Lightweight Sharpness-Aware Approach for Multi-Task Optimization with Joint Global-Local Perturbation

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-05-18T12:01:21.199581Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ad6d4819-7203-4f52-8aa6-28dabf3b6402 · outbound

This paper cites Fedalt: Federated fine-tuning through adaptive local training with rest-of-world lora.arXiv preprint arXiv:2503.11880.

Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs Fedalt: Federated fine-tuning through adaptive local training with rest-of-world lora.arXiv preprint arXiv:2503.11880

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-18T12:01:21.140671Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 7ae9456a-0b9b-4c0b-b950-ebaa72fc891b · outbound

This paper cites Gradient-Based Multi-Objective Deep Learning: Algorithms, Theories, Applications, and Beyond.

Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs Gradient-Based Multi-Objective Deep Learning: Algorithms, Theories, Applications, and Beyond

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-18T12:01:21.183657Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 372d923f-7c7a-4b6e-9283-9c2512cdabfb · outbound

This paper cites Heterogeneous lora for fed- erated fine-tuning of on-device foundation models.

Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs Heterogeneous lora for fed- erated fine-tuning of on-device foundation models

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T12:01:21.784918Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 186053ec-877b-4abb-8a83-d456d4fcd029 · outbound

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

Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs Boolq: Exploring the surprising difficulty of natural yes/no questions

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T12:01:21.791673Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 5e59e526-6acb-470b-a100-c7b13f104856 · outbound

This paper cites Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge.

Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-05-18T12:01:21.110278Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 0838c22e-0a89-42b2-b7a4-93ca3adacae7 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs Training Verifiers to Solve Math Word Problems

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-05-18T12:01:21.177823Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 3921b301-dffc-4911-88e6-0c49342c77ae · outbound

This paper cites Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities.

Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-05-18T12:01:21.172839Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 187f6b39-1f88-4e10-928d-551f3ae33ccf · outbound

This paper cites Dongshang Deng, Xuangou Wu, Tao Zhang, Xiangyun Tang, Hongyang Du, Jiawen Kang, Jiqiang Liu, and Dusit Niyato.

Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs Dongshang Deng, Xuangou Wu, Tao Zhang, Xiangyun Tang, Hongyang Du, Jiawen Kang, Jiqiang Liu, and Dusit Niyato

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T12:01:21.740795Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation f37c0fe3-5a71-49c8-b43b-d3abe593cd42 · outbound

This paper cites Loramoe: Alleviating world knowledge forgetting in large language models via moe-style plugin.

Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs Loramoe: Alleviating world knowledge forgetting in large language models via moe-style plugin

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T12:01:21.774267Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation bd35b123-6067-4155-a080-d727af6e3a25 · outbound

This paper cites Llm-adapters: An adapter family for parameter-efficient fine-tuning of large language models.

Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs Llm-adapters: An adapter family for parameter-efficient fine-tuning of large language models

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T12:01:21.777646Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 59869abe-c2b2-44c0-953c-eeebefffa063 · outbound

This paper cites Mawps: A math word problem repository.

Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs Mawps: A math word problem repository

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T12:01:21.770714Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 9e6013b3-4c68-4b14-95db-6dd6c78cc3c9 · outbound

This paper cites The power of scale for parameter-efficient prompt tuning.

Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs The power of scale for parameter-efficient prompt tuning

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T12:01:21.767604Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 685ce54f-051d-4972-8d7f-008f9a1dd5d3 · outbound

This paper cites LotteryFL: Personalized and Communication-Efficient Federated Learning with Lottery Ticket Hypothesis on Non-IID Datasets.

Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs LotteryFL: Personalized and Communication-Efficient Federated Learning with Lottery Ticket Hypothesis on Non-IID Datasets

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-18T12:01:21.167519Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation fc4d66da-3ffd-4d03-93c9-f81682b2a87b · outbound

This paper cites DynMoLE: Boosting Mixture of LoRA Experts Fine-Tuning with a Hybrid Routing Mechanism.

Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs DynMoLE: Boosting Mixture of LoRA Experts Fine-Tuning with a Hybrid Routing Mechanism

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-18T12:01:21.151871Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 526aa889-1e83-45c5-87ec-6a6aa6ebea00 · outbound

This paper cites Bgefl: Enabling communication-efficient federated learning via bandit gradient estimation in resource-constrained networks.IEEE Transactions on Networking, 2025b.

Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs Bgefl: Enabling communication-efficient federated learning via bandit gradient estimation in resource-constrained networks.IEEE Transactions on Networking, 2025b

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-18T12:01:21.130205Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 6c75303b-ed94-44a0-a3eb-73df5018b2ba · outbound

This paper cites MoELoRA: Contrastive Learning Guided Mixture of Experts on Parameter-Efficient Fine-Tuning for Large Language Models.

Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs MoELoRA: Contrastive Learning Guided Mixture of Experts on Parameter-Efficient Fine-Tuning for Large Language Models

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-18T12:01:21.205507Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 6a2313bb-4323-4ba5-aa90-7435628dae61 · outbound

This paper cites Can a suit of armor conduct elec- tricity? a new dataset for open book question answering.

Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs Can a suit of armor conduct elec- tricity? a new dataset for open book question answering

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T12:01:21.761119Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 9ff972c6-0526-4b26-88db-982ef39e79f7 · outbound

This paper cites an unresolved cited work.

Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs Unresolved cited work

Reference 20

Resolution: unresolved; raw_fallback, observed 2026-05-18T12:01:21.764386Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 18b91ce3-806c-4ada-8229-d1718ec2ee62 · outbound

This paper cites Improving multi-task learning via seeking task-based flat regions.arXiv preprint arXiv:2211.13723.

Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs Improving multi-task learning via seeking task-based flat regions.arXiv preprint arXiv:2211.13723

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-05-18T12:01:21.157079Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation e722d1cf-9d38-445f-98be-c443225ba0ba · outbound

This paper cites Ravan: Multi-head low-rank adaptation for federated fine-tuning.arXiv preprint arXiv:2506.05568.

Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs Ravan: Multi-head low-rank adaptation for federated fine-tuning.arXiv preprint arXiv:2506.05568

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-05-18T12:01:21.146573Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 29e6820c-a3e9-4c8d-8e4d-919e5266e0ed · outbound

This paper cites Social iqa: Common- sense reasoning about social interactions.

Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs Social iqa: Common- sense reasoning about social interactions

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T12:01:21.757865Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation f9f7e3dc-10f1-49e3-a115-70a74f0f6c9e · outbound

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

Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-05-18T12:01:21.134824Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation d892b6ba-d1b1-4f92-a28e-05348fb5f3ae · outbound

This paper cites Aprompt: Attention prompt tuning for efficient adaptation of pre-trained language models.

Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs Aprompt: Attention prompt tuning for efficient adaptation of pre-trained language models

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T12:01:21.747897Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation b4093c47-ee5a-4fdf-83cb-7a4e3b41a684 · outbound

This paper cites Mixture-of-subspaces in low-rank adapta- tion.

Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs Mixture-of-subspaces in low-rank adapta- tion

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T12:01:21.751536Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ef7be5d3-7969-4f74-bc2a-59239d0127c4 · outbound

This paper cites Low-rank adaptation for foundation models: A comprehensive review.arXiv preprint arXiv:2501.00365.

Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs Low-rank adaptation for foundation models: A comprehensive review.arXiv preprint arXiv:2501.00365

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-05-18T12:01:21.124931Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation c436db0d-d2d5-400e-a280-6014667a2a94 · outbound

This paper cites MoRE: A Mixture of Low-Rank Experts for Adaptive Multi-Task Learning.

Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs MoRE: A Mixture of Low-Rank Experts for Adaptive Multi-Task Learning

Reference 28

Resolution: verified exact; arxiv_id, observed 2026-05-18T12:01:21.193961Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 0ab99250-ab6f-4360-a65b-314433ffc06c · outbound

This paper cites Fed-HeLLo: Efficient Federated Foundation Model Fine-Tuning with Heterogeneous LoRA Allocation.

Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs Fed-HeLLo: Efficient Federated Foundation Model Fine-Tuning with Heterogeneous LoRA Allocation

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-05-18T12:01:21.162053Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 975b06d7-dae1-43c9-ac5c-5da8b03fdc4a · outbound

This paper cites Delta-LoRA: Fine-Tuning High-Rank Parameters with the Delta of Low-Rank Matrices.

Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs Delta-LoRA: Fine-Tuning High-Rank Parameters with the Delta of Low-Rank Matrices

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-18T12:01:21.118378Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation b9735c9b-2e2e-4686-afe5-51f04a0a402d · outbound

This paper cites SUPPLEMENTARYMATERIALS A ADDITIONALRELATEDWORK Parameter-efficient fine-tuning.

Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs SUPPLEMENTARYMATERIALS A ADDITIONALRELATEDWORK Parameter-efficient fine-tuning

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T12:01:21.733877Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 82ec64cf-a1dc-4526-a272-4f6233cc0206 · outbound

This paper cites an unresolved cited work.

Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs Unresolved cited work

Reference 32

Resolution: unresolved; raw_fallback, observed 2026-05-18T12:01:21.754442Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation a6b11bd9-ca5d-45c9-9d54-fb087e9df5b6 · outbound

This paper cites Other methods examine MTL from the perspective of label noise (He et al., 2024), fairness (Navon et al., 2022; Ban & Ji.

Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs Other methods examine MTL from the perspective of label noise (He et al., 2024), fairness (Navon et al., 2022; Ban & Ji

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T12:01:21.788534Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 2aa67e03-1d8a-48b1-991b-8969769a5424 · outbound

This paper cites Federated learning.

Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs Federated learning

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T12:01:21.781242Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 17cf1b36-6679-4679-983a-c7244e53c8ad · outbound

This paper cites 10.0% CloQA 40.1% GenQA50.0% IE 24.8% OpnQA 25.3% Figure 7: Data distribution of clients.

Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs 10.0% CloQA 40.1% GenQA50.0% IE 24.8% OpnQA 25.3% Figure 7: Data distribution of clients

Reference 35

Resolution: malformed identifier; raw_fallback, observed 2026-05-18T12:01:21.737583Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation bc5bfe00-3a82-45b8-8d8d-ab2eadc5cd61 · outbound

This paper cites The methods are applied toq proj andv proj modules.

Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs The methods are applied toq proj andv proj modules

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-05-18T12:01:21.744355Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Pith citing papers

Observation 314344af-6f1d-48f2-8668-81b41432acdd · inbound

Collaborative and Efficient Fine-tuning: Leveraging Task Similarity cites this paper.

Collaborative and Efficient Fine-tuning: Leveraging Task Similarity Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-03T03:49:39.658872Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e13dd72-06d9-4a50-a590-2089c1cca623 · inbound

Unified Gradient Projection: Language-Balanced Continual Learning for Multilingual Low-Resource ASR cites this paper.

Unified Gradient Projection: Language-Balanced Continual Learning for Multilingual Low-Resource ASR Rethinking Parameter Sharing for LLM Fine-Tuning with Multiple LoRAs

Reference 20

Resolution: unresolved; no resolver link, observed 2026-07-14T06:34:55.089754Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.