Paper Citation Record · LEDGER

Fast Large Language Model Collaborative Decoding via Speculation

As of 14 August 2026, this Paper Citation Record lists 42 of 42 outbound references and 7 inbound Pith citation observations for arXiv:2502.01662.

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

pith.paper-citation-record.v1
2502.01662 v2

Coverage vector

measured 42 of 42 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-09T19:34:42.923184Z

measured 49 of 49 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-14T06:32:32.682623+00:00

measured 7 of 7 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-11T20:20:19.183308Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-01T08:15:32.154273Z

Reference resolution

42 of 42 outbound references displayed

verified exact0
verified fuzzy14
unresolved28
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 49871604-9da7-4e22-9b0d-e314f0068ade · outbound

This paper cites GPT-4 Technical Report.

Fast Large Language Model Collaborative Decoding via Speculation GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-09T19:34:42.718344Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7aa4dc56-7a14-49d8-bfd5-489dc2304b41 · outbound

This paper cites Optimized multi-token joint decoding with auxiliary model for llm inference.

Fast Large Language Model Collaborative Decoding via Speculation Optimized multi-token joint decoding with auxiliary model for llm inference

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T19:34:43.573707Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation ae8786af-4db5-4dae-ac23-998c72282bbc · outbound

This paper cites Judge decoding: Faster speculative sampling requires going beyond model alignment.

Fast Large Language Model Collaborative Decoding via Speculation Judge decoding: Faster speculative sampling requires going beyond model alignment

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T19:34:43.557785Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 04428c34-ab39-4d2a-ba7b-65186a07b5c2 · outbound

This paper cites Qwen Technical Report.

Fast Large Language Model Collaborative Decoding via Speculation Qwen Technical Report

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-09T19:34:42.734335Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a3a0a72-5f5f-4ef9-b8db-465d01b864f3 · outbound

This paper cites D., Chen, D., and Dao, T.

Fast Large Language Model Collaborative Decoding via Speculation D., Chen, D., and Dao, T

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T19:34:43.541076Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation d5b976c1-93b1-48db-85ef-b1d084624ca6 · outbound

This paper cites FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance.

Fast Large Language Model Collaborative Decoding via Speculation FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-09T19:34:42.751817Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf78432b-2df7-41ec-9ecd-33183fcdfe82 · outbound

This paper cites an unresolved cited work.

Fast Large Language Model Collaborative Decoding via Speculation Unresolved cited work

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-09T19:34:42.756975Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a4739842-7586-40bf-8294-ccc7371d628c · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Fast Large Language Model Collaborative Decoding via Speculation Training Verifiers to Solve Math Word Problems

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-09T19:34:42.761775Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eec7d799-9a97-44c5-bc9f-91d2f33b4537 · outbound

This paper cites Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing.

Fast Large Language Model Collaborative Decoding via Speculation Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-09T19:34:42.766560Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 252909aa-7469-4e0b-bd55-20a0f166ef01 · outbound

This paper cites The Llama 3 Herd of Models.

Fast Large Language Model Collaborative Decoding via Speculation The Llama 3 Herd of Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-09T19:34:42.771328Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23dd7218-7081-46fd-b675-6f638150924e · outbound

This paper cites Layerskip: Enabling early exit inference and self-speculative decoding.

Fast Large Language Model Collaborative Decoding via Speculation Layerskip: Enabling early exit inference and self-speculative decoding

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T19:34:43.514791Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 748291ee-edbe-449d-a385-b5fc5f86673f · outbound

This paper cites Llm-topla: Efficient llm ensemble by maximising diversity.

Fast Large Language Model Collaborative Decoding via Speculation Llm-topla: Efficient llm ensemble by maximising diversity

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T19:34:43.498782Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation d40c8953-5ab6-4f82-bfdb-b9a654dced8d · outbound

This paper cites Graph-structured speculative decoding.

Fast Large Language Model Collaborative Decoding via Speculation Graph-structured speculative decoding

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T19:34:43.482971Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation a33534c7-7f12-43c4-8123-8d23427725b5 · outbound

This paper cites Measuring massive multitask language understanding.

Fast Large Language Model Collaborative Decoding via Speculation Measuring massive multitask language understanding

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-09T19:34:42.789550Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75fa5e1c-755e-483e-92e0-46360856478e · outbound

This paper cites and Huang, H.

Fast Large Language Model Collaborative Decoding via Speculation and Huang, H

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T19:34:43.454728Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation b6bf4570-b47d-4935-b25b-c2f6001300c1 · outbound

This paper cites an unresolved cited work.

Fast Large Language Model Collaborative Decoding via Speculation Unresolved cited work

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-09T19:34:42.798452Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb7fb685-553c-47a5-a86f-386059aa2797 · outbound

This paper cites an unresolved cited work.

Fast Large Language Model Collaborative Decoding via Speculation Unresolved cited work

Reference 18

Resolution: unresolved; raw_fallback, observed 2026-08-09T19:34:43.427208Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation fb261483-57e6-4297-a5e1-62adc71cd95d · outbound

This paper cites Fast inference from transformers via speculative decoding.

Fast Large Language Model Collaborative Decoding via Speculation Fast inference from transformers via speculative decoding

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T19:34:43.411677Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e412d72e-990f-4846-b9d3-f9aedcdc5b8e · outbound

This paper cites Purifying Large Language Models by Ensembling a Small Language Model.

Fast Large Language Model Collaborative Decoding via Speculation Purifying Large Language Models by Ensembling a Small Language Model

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-09T19:34:42.813056Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e2fa5d1-4094-48c8-b91f-d876e514fcb6 · outbound

This paper cites L., Holtzman, A., Fried, D., Liang, P., Eisner, J., Hashimoto, T.

Fast Large Language Model Collaborative Decoding via Speculation L., Holtzman, A., Fried, D., Liang, P., Eisner, J., Hashimoto, T

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T19:34:43.394793Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 67c3f56f-e88c-46de-993f-27dfadf9262b · outbound

This paper cites Eagle: Speculative sampling requires rethinking feature uncertainty.

Fast Large Language Model Collaborative Decoding via Speculation Eagle: Speculative sampling requires rethinking feature uncertainty

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T19:34:43.379561Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 4b49196a-229e-40f8-82bd-750fbf7533be · outbound

This paper cites Eagle-2: Faster inference of language models with dynamic draft trees.

Fast Large Language Model Collaborative Decoding via Speculation Eagle-2: Faster inference of language models with dynamic draft trees

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T19:34:43.364261Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 48bfff0f-49b9-468d-981c-56d669518c22 · outbound

This paper cites DeepSeek-V3 Technical Report.

Fast Large Language Model Collaborative Decoding via Speculation DeepSeek-V3 Technical Report

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-09T19:34:42.831914Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02f97edf-a985-47ca-a27f-00e711e5f0be · outbound

This paper cites Merge, Ensemble, and Cooperate! A Survey on Collaborative Strategies in the Era of Large Language Models.

Fast Large Language Model Collaborative Decoding via Speculation Merge, Ensemble, and Cooperate! A Survey on Collaborative Strategies in the Era of Large Language Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-09T19:34:42.836845Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2b8a880-4c2a-4ee9-a89f-fe0377bb164d · outbound

This paper cites Routing to the Expert: Efficient Reward-guided Ensemble of Large Language Models.

Fast Large Language Model Collaborative Decoding via Speculation Routing to the Expert: Efficient Reward-guided Ensemble of Large Language Models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-09T19:34:42.841795Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9bdd421b-f85f-437f-a567-40302a9d35e4 · outbound

This paper cites Blending Is All You Need: Cheaper, Better Alternative to Trillion-Parameters LLM.

Fast Large Language Model Collaborative Decoding via Speculation Blending Is All You Need: Cheaper, Better Alternative to Trillion-Parameters LLM

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-09T19:34:42.846637Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 72939cfb-f673-4b09-9f62-2d5fa45a280a · outbound

This paper cites an unresolved cited work.

Fast Large Language Model Collaborative Decoding via Speculation Unresolved cited work

Reference 28

Resolution: unresolved; raw_fallback, observed 2026-08-09T19:34:43.348336Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 77f8a8d3-87c7-455c-954d-c70c8b7efd55 · outbound

This paper cites Accelerating Large Language Model Decoding with Speculative Sampling.

Fast Large Language Model Collaborative Decoding via Speculation Accelerating Large Language Model Decoding with Speculative Sampling

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-09T19:34:42.856186Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03a5b853-f377-4768-98d3-6931b2cf520e · outbound

This paper cites J., and Manning, C.

Fast Large Language Model Collaborative Decoding via Speculation J., and Manning, C

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-09T19:34:42.860706Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27ebf683-fdb2-41a6-ac28-69759eb4949c · outbound

This paper cites Large language model routing with benchmark datasets.

Fast Large Language Model Collaborative Decoding via Speculation Large language model routing with benchmark datasets

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T19:34:43.332303Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation b2c7f695-12f1-424e-8de9-df01264d1df0 · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

Fast Large Language Model Collaborative Decoding via Speculation Gemini: A Family of Highly Capable Multimodal Models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-09T19:34:42.870039Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05fe3f58-a276-4ef0-8fb0-82ff86f795d5 · outbound

This paper cites Qwen2.5: A party of foundation models, September 2024.

Fast Large Language Model Collaborative Decoding via Speculation Qwen2.5: A party of foundation models, September 2024

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-09T19:34:42.874887Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 090bae2a-49ad-4bf2-8af7-c14f962c974b · outbound

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

Fast Large Language Model Collaborative Decoding via Speculation Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-09T19:34:42.879635Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a18cd2b1-401e-46a9-a9ed-6ccf3ad43396 · outbound

This paper cites MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation.

Fast Large Language Model Collaborative Decoding via Speculation MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-09T19:34:42.884194Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ea745e2-d4ab-4b09-9eec-151ba1c3f0d7 · outbound

This paper cites Generation Meets Verification: Accelerating Large Language Model Inference with Smart Parallel Auto-Correct Decoding.

Fast Large Language Model Collaborative Decoding via Speculation Generation Meets Verification: Accelerating Large Language Model Inference with Smart Parallel Auto-Correct Decoding

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-09T19:34:42.889215Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1127ae5f-789a-4bfa-bd84-6e73b7bd718e · outbound

This paper cites C., Ziqi, Y., Yucheng, C., and Li, Y.-S.

Fast Large Language Model Collaborative Decoding via Speculation C., Ziqi, Y., Yucheng, C., and Li, Y.-S

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-09T19:34:42.894227Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb5975f4-8907-4908-ab98-6f337af84a9f · outbound

This paper cites Speculative contrastive decoding.

Fast Large Language Model Collaborative Decoding via Speculation Speculative contrastive decoding

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-09T19:34:42.899070Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9de50db-3336-40d3-915a-dcebf95d5daf · outbound

This paper cites Draft&verify: Lossless large language model acceleration via self-speculative decoding.

Fast Large Language Model Collaborative Decoding via Speculation Draft&verify: Lossless large language model acceleration via self-speculative decoding

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T19:34:43.305285Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation fd20c50e-dc9e-4d74-bfff-c787c4675911 · outbound

This paper cites V., Mihaylov, T., Ott, M., Shleifer, S., Shuster, K., Simig, D., Koura, P.

Fast Large Language Model Collaborative Decoding via Speculation V., Mihaylov, T., Ott, M., Shleifer, S., Shuster, K., Simig, D., Koura, P

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-09T19:34:42.908917Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30691e11-0381-4fe2-9c08-9a63eecc2e8a · outbound

This paper cites P., Zhang, H., Gonzalez, J.

Fast Large Language Model Collaborative Decoding via Speculation P., Zhang, H., Gonzalez, J

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-09T19:34:42.913554Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11d3e7c9-1227-4859-ae1a-6560d4efc7e6 · outbound

This paper cites S., Menon, A., Rostamizadeh, A., Kumar, S., Kagy, J.-F., and Agarwal, R.

Fast Large Language Model Collaborative Decoding via Speculation S., Menon, A., Rostamizadeh, A., Kumar, S., Kagy, J.-F., and Agarwal, R

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T19:34:43.267902Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation c9fcbd5e-9ba1-411f-8df0-3a967ae10fac · outbound

This paper cites write newline.

Fast Large Language Model Collaborative Decoding via Speculation write newline

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-09T19:34:42.923184Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation c7344fe2-73aa-4952-8948-c3ad8ce35ac5 · inbound

PBI-Attack: Prior-Guided Bimodal Interactive Black-Box Jailbreak Attack for Toxicity Maximization cites this paper.

PBI-Attack: Prior-Guided Bimodal Interactive Black-Box Jailbreak Attack for Toxicity Maximization Fast Large Language Model Collaborative Decoding via Speculation

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-11T20:20:19.183308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 571f5654-e954-4b8c-aeb2-2456940e7102 · inbound

Multimodal Tabular Reasoning with Privileged Structured Information cites this paper.

Multimodal Tabular Reasoning with Privileged Structured Information Fast Large Language Model Collaborative Decoding via Speculation

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T10:53:58.892122Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54d16537-58a6-40ee-901d-fa6a88501dbf · inbound

SignAligner: Harmonizing Complementary Pose Modalities for Coherent Sign Language Generation cites this paper.

SignAligner: Harmonizing Complementary Pose Modalities for Coherent Sign Language Generation Fast Large Language Model Collaborative Decoding via Speculation

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T04:10:11.741454Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 684a0bb9-e8f3-4fb3-98b2-7ac8e6982251 · inbound

AnchorSeg: Language Grounded Query Banks for Reasoning Segmentation cites this paper.

AnchorSeg: Language Grounded Query Banks for Reasoning Segmentation Fast Large Language Model Collaborative Decoding via Speculation

Reference 58

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T09:43:49.444527Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 7ed78080-faf4-480a-b385-14755324412a · inbound

SpecFed: Accelerating Federated LLM Inference with Speculative Decoding and Compressed Transmission cites this paper.

SpecFed: Accelerating Federated LLM Inference with Speculative Decoding and Compressed Transmission Fast Large Language Model Collaborative Decoding via Speculation

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-12T00:31:17.251029Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 4c1f544c-6ebb-4f79-ab83-08e5ecbad181 · inbound

Rethinking LLM Ensembling from the Perspective of Mixture Models cites this paper.

Rethinking LLM Ensembling from the Perspective of Mixture Models Fast Large Language Model Collaborative Decoding via Speculation

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-07-01T08:15:32.157274Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 9f275b1b-19c2-4763-b4dc-173b72f56d06 · inbound

Revisiting Lossy Verification in Speculative Decoding: Mechanisms, Trade-offs, and Failure Modes cites this paper.

Revisiting Lossy Verification in Speculative Decoding: Mechanisms, Trade-offs, and Failure Modes Fast Large Language Model Collaborative Decoding via Speculation

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-01T12:07:01.364373Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.