Paper Citation Record · LEDGER

LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression

As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 36 inbound Pith citation observations for arXiv:2403.12968.

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

pith.paper-citation-record.v1
2403.12968 v2

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 36 of 36 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 36 of 36 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-08T19:28:43.581431Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-10T01:36:44.313151Z

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation 39a663c5-0200-42f1-856a-ae6d7ff071d7 · inbound

APE: Faster and Longer Context-Augmented Generation via Adaptive Parallel Encoding cites this paper.

APE: Faster and Longer Context-Augmented Generation via Adaptive Parallel Encoding LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-08T19:28:43.581431Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b02d16ea-81c7-4edd-b095-22e915bac0b1 · inbound

On Memory Construction and Retrieval for Personalized Conversational Agents cites this paper.

On Memory Construction and Retrieval for Personalized Conversational Agents LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-08T18:46:28.123214Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3142ecc6-0433-4587-91e7-a8e8b15b0f06 · inbound

Beyond Hard and Soft: Hybrid Context Compression for Balancing Local and Global Information Retention cites this paper.

Beyond Hard and Soft: Hybrid Context Compression for Balancing Local and Global Information Retention LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:58.091882Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91af50d8-c748-4a84-b7eb-2de52c9b2252 · inbound

QwenLong-CPRS: Towards $\infty$-LLMs with Dynamic Context Optimization cites this paper.

QwenLong-CPRS: Towards $\infty$-LLMs with Dynamic Context Optimization LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T14:40:54.196360Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f8883e8-3d0d-4123-bd8e-e429ca5f5517 · inbound

A Survey of LLM $\times$ DATA cites this paper.

A Survey of LLM $\times$ DATA LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression

Reference 303

Resolution: unresolved; no resolver link, observed 2026-08-07T14:33:13.556578Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68c2a5b1-9cd9-4e65-8b2e-a291a8194b5f · inbound

Concise Reasoning, Big Gains: Pruning Long Reasoning Trace with Difficulty-Aware Prompting cites this paper.

Concise Reasoning, Big Gains: Pruning Long Reasoning Trace with Difficulty-Aware Prompting LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T14:12:23.078185Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7834589b-7ae5-42c2-9a10-b13825ec2e6b · inbound

Lossless Token Sequence Compression via Meta-Tokens cites this paper.

Lossless Token Sequence Compression via Meta-Tokens LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T12:14:28.276503Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6d45ce7-ba34-4679-bd80-49b8aa172fb1 · inbound

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation cites this paper.

EPiC: Towards Lossless Speedup for Reasoning Training through Edge-Preserving CoT Condensation LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-07T10:52:49.739784Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c725764d-15c9-4436-86f3-71b3122f0f4b · inbound

Cartridges: Lightweight and general-purpose long context representations via self-study cites this paper.

Cartridges: Lightweight and general-purpose long context representations via self-study LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-07T06:04:33.533062Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e92313e-80ee-4f48-b44d-86c392db01ef · inbound

Not All Errors Are Created Equal: ASCoT Addresses Late-Stage Fragility in Efficient LLM Reasoning cites this paper.

Not All Errors Are Created Equal: ASCoT Addresses Late-Stage Fragility in Efficient LLM Reasoning LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-05T23:32:55.108925Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bdb866a6-6bd4-41c9-9199-da7c783235eb · inbound

Can Reasoning Path still be Effective as Input? Bridging Post-Reasoning to Chain-of-Thought Compression cites this paper.

Can Reasoning Path still be Effective as Input? Bridging Post-Reasoning to Chain-of-Thought Compression LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-04T10:56:59.953094Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6b81bd0-a923-4fa5-9354-92f5e1a34ea4 · inbound

ARC-Encoder: learning compressed text representations for large language models cites this paper.

ARC-Encoder: learning compressed text representations for large language models LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-04T08:28:51.479132Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 432a6a4a-194f-44ae-9aa8-d78a4b47853a · inbound

When Compression Becomes an Attack Surface: Black-Box Attacks on Prompt-Compressed LLM Agents cites this paper.

When Compression Becomes an Attack Surface: Black-Box Attacks on Prompt-Compressed LLM Agents LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-04T08:06:13.382693Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21a3fcdd-9853-4fe8-a855-7aa3109374fc · inbound

Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression cites this paper.

Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-21T13:44:11.429005Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 177561b4-6493-4f29-9d35-87c6eb984f55 · inbound

Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression cites this paper.

Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-03T03:25:23.085492Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ffbf7176-4647-4850-a649-81291c07f1ed · inbound

HyMem: Hybrid Memory Architecture with Dynamic Retrieval Scheduling cites this paper.

HyMem: Hybrid Memory Architecture with Dynamic Retrieval Scheduling LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-15T22:00:21.370606Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 5e91b903-6dde-45a6-bee9-ce1f4ed19c1e · inbound

On the Effectiveness of Context Compression for Repository-Level Tasks: An Empirical Investigation cites this paper.

On the Effectiveness of Context Compression for Repository-Level Tasks: An Empirical Investigation LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression

Reference 27

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T13:40:27.550032Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation a9b88b44-388d-4eab-9cbb-78f61ccaff25 · inbound

Compressed-Sensing-Guided, Inference-Aware Structured Reduction for Large Language Models cites this paper.

Compressed-Sensing-Guided, Inference-Aware Structured Reduction for Large Language Models LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-15T06:55:10.703875Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation f8b0b7ae-33cd-4e33-9738-173ada693d76 · inbound

MemoSight: Unifying Context Compression and Multi Token Prediction for Reasoning Acceleration cites this paper.

MemoSight: Unifying Context Compression and Multi Token Prediction for Reasoning Acceleration LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression

Reference 2

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T11:30:18.723446Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation b260708b-3f16-40b5-a26a-d49afaf4431b · inbound

Compressing Sequences in the Latent Embedding Space: $K$-Token Merging for Large Language Models cites this paper.

Compressing Sequences in the Latent Embedding Space: $K$-Token Merging for Large Language Models LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression

Reference 3

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T11:30:18.902593Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 8033894c-d87e-407f-8b63-666c2d8fc9b4 · inbound

CRISP: Compressing Redundancy in Chain-of-Thought via Intrinsic Saliency Pruning cites this paper.

CRISP: Compressing Redundancy in Chain-of-Thought via Intrinsic Saliency Pruning LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression

Reference 3

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T05:41:02.315060Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 2b3aa798-8e11-44d1-8c35-96b165c54f5c · inbound

ONTO: A Token-Efficient Columnar Notation for LLM Input Optimization cites this paper.

ONTO: A Token-Efficient Columnar Notation for LLM Input Optimization LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-10T09:23:37.772862Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 55ee1889-ec1c-42e7-affe-0b2fb3828c50 · inbound

Byte-Exact Deduplication in Retrieval-Augmented Generation: A Three-Regime Empirical Analysis Across Public Benchmarks cites this paper.

Byte-Exact Deduplication in Retrieval-Augmented Generation: A Three-Regime Empirical Analysis Across Public Benchmarks LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:26:24.135636Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 9376042f-6697-43da-9e11-328cac3acd36 · inbound

SOMA: Efficient Multi-turn LLM Serving via Small Language Model cites this paper.

SOMA: Efficient Multi-turn LLM Serving via Small Language Model LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression

Reference 37

Resolution: verified exact; arxiv_id, observed 2026-05-13T01:42:04.141168Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation e74ad4b0-1431-4ba4-8d7d-e2db439ba6ce · inbound

Tool-Schema Compression Enables Agentic RAG Under Constrained Context Budgets cites this paper.

Tool-Schema Compression Enables Agentic RAG Under Constrained Context Budgets LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression

Reference 15

Resolution: metadata mismatch; arxiv_id, observed 2026-06-29T23:24:01.261450Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 7be9e403-d430-4e0a-b55a-aa0b31712b53 · inbound

Optical Reasoning: Rethinking Images as an Expressive Reasoning Medium Beyond Text cites this paper.

Optical Reasoning: Rethinking Images as an Expressive Reasoning Medium Beyond Text LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression

Reference 31

Resolution: verified exact; arxiv_id, observed 2026-07-03T01:17:30.496481Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 872176f3-7bb5-42b0-98aa-d158a673f289 · inbound

HMARS: A Hierarchical Multi-Agent Memory System for Long-Context Reasoning cites this paper.

HMARS: A Hierarchical Multi-Agent Memory System for Long-Context Reasoning LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-06-30T11:34:37.875806Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 876ee509-ace5-4827-92f2-b35936117c4b · inbound

Mapping Text to Multiplex Graph: Prompt Compression as L\'evy Walk-Guided Graph Pruning cites this paper.

Mapping Text to Multiplex Graph: Prompt Compression as L\'evy Walk-Guided Graph Pruning LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-07-04T01:49:21.537057Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 1348a19c-38f4-49d1-a68c-3ab61dca1a57 · inbound

Consistent but Miscalibrated: Evaluating LLM Limitations for Risk Communication in Natural Language cites this paper.

Consistent but Miscalibrated: Evaluating LLM Limitations for Risk Communication in Natural Language LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression

Reference 185

Resolution: unresolved; no resolver link, observed 2026-07-11T23:16:58.545731Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2cd86c4a-566f-41e6-96c1-71363b128d70 · inbound

Consistent but Miscalibrated: Evaluating LLM Limitations for Risk Communication in Natural Language cites this paper.

Consistent but Miscalibrated: Evaluating LLM Limitations for Risk Communication in Natural Language LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression

Reference 185

Resolution: unresolved; no resolver link, observed 2026-07-13T07:02:13.140334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a44aaba4-ac7e-4e0a-841a-4e08e1740801 · inbound

What to Keep, What to Forget: A Rate--Distortion View of Memory Compaction in LLMs and Agents cites this paper.

What to Keep, What to Forget: A Rate--Distortion View of Memory Compaction in LLMs and Agents LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression

Reference 91

Resolution: metadata mismatch; local_arxiv, observed 2026-07-10T01:36:44.314393Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 9766d172-1b11-4e2b-af13-568746610d34 · inbound

Mach-Mind-4-Flash Technical Report cites this paper.

Mach-Mind-4-Flash Technical Report LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression

Reference 30

Resolution: unresolved; no resolver link, observed 2026-07-13T03:29:34.486347Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b494edfa-de78-40f7-b727-7bdf014fe5de · inbound

Spectral-LSH: Sub-Quadratic Prompt Compression via Krylov-Projected Locality-Sensitive Hashing cites this paper.

Spectral-LSH: Sub-Quadratic Prompt Compression via Krylov-Projected Locality-Sensitive Hashing LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-02T11:37:07.776703Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d15fd6a5-32d9-48b5-a2ac-443aad570904 · inbound

Floor, Ceiling, and the Fusion Gap: How Much of Crowd Reading Attention Can Machines Predict? cites this paper.

Floor, Ceiling, and the Fusion Gap: How Much of Crowd Reading Attention Can Machines Predict? LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-04T22:38:10.188571Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47e4c23b-3a55-45d2-87e4-57d13081b489 · inbound

Lightweight Chunk Selection for Mobile Retrieval-Augmented Generation cites this paper.

Lightweight Chunk Selection for Mobile Retrieval-Augmented Generation LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T00:45:23.991669Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83425617-64bf-477f-8aa1-5da4aeccd405 · inbound

SkillZip: Contract-Preserving Graph Compression for Scalable Agent Skill Libraries cites this paper.

SkillZip: Contract-Preserving Graph Compression for Scalable Agent Skill Libraries LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-08T05:45:36.152929Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.