Paper Citation Record · LEDGER

Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibration

As of 23 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 17 inbound Pith citation observations for arXiv:2406.15765.

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

pith.paper-citation-record.v1
2406.15765 v1

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 17 of 17 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-23T06:30:58.430688+00:00

measured 17 of 17 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-16T01:07:10.338919Z

measured 1 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

0 of 0 outbound references displayed

verified exact0
verified fuzzy0
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

1
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

No outbound reference observations are available for this paper version.

Pith citing papers

Observation f38c3829-aa08-4079-a839-31f36f9f0574 · inbound

When Attention Sink Emerges in Language Models: An Empirical View cites this paper.

When Attention Sink Emerges in Language Models: An Empirical View Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibration

Reference 58

Resolution: verified exact; arxiv_id, observed 2026-05-16T17:41:03.780096Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 8dae5ba5-8f92-49ef-b141-71c705dc3706 · inbound

Seeing Clearly by Layer Two: Enhancing Attention Heads to Alleviate Hallucination in LVLMs cites this paper.

Seeing Clearly by Layer Two: Enhancing Attention Heads to Alleviate Hallucination in LVLMs Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibration

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-12T20:12:25.386894Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f379fb86-6723-4b09-8d16-9290b406a22e · inbound

Mirage in the Eyes: Hallucination Attack on Multi-modal Large Language Models with Only Attention Sink cites this paper.

Mirage in the Eyes: Hallucination Attack on Multi-modal Large Language Models with Only Attention Sink Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibration

Reference 95

Resolution: unresolved; no resolver link, observed 2026-08-10T14:29:28.318562Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18a42c33-689b-4027-9e27-082b3c1e12de · inbound

RotateKV: Accurate and Robust 2-Bit KV Cache Quantization for LLMs via Outlier-Aware Adaptive Rotations cites this paper.

RotateKV: Accurate and Robust 2-Bit KV Cache Quantization for LLMs via Outlier-Aware Adaptive Rotations Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibration

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-10T14:54:22.742657Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a459b328-50c2-45d6-863c-d30756b4087a · inbound

Attention Mechanisms Perspective: Exploring LLM Processing of Graph-Structured Data cites this paper.

Attention Mechanisms Perspective: Exploring LLM Processing of Graph-Structured Data Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibration

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-16T01:07:10.338919Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb7ced7d-ba12-4b48-bdbf-06d6db0d3e7e · inbound

Probability Consistency in Large Language Models: Theoretical Foundations Meet Empirical Discrepancies cites this paper.

Probability Consistency in Large Language Models: Theoretical Foundations Meet Empirical Discrepancies Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibration

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-15T21:55:30.374903Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b3b67f3-291b-40f7-8796-9667f427ba3a · inbound

MCA-LLaVA: Manhattan Causal Attention for Reducing Hallucination in Large Vision-Language Models cites this paper.

MCA-LLaVA: Manhattan Causal Attention for Reducing Hallucination in Large Vision-Language Models Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibration

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-06T18:09:11.418491Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad1d02ba-5b0a-4a91-a233-34fc83234a39 · inbound

Enhancing Chain-of-Thought Reasoning with Critical Representation Fine-tuning cites this paper.

Enhancing Chain-of-Thought Reasoning with Critical Representation Fine-tuning Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibration

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-06T17:52:38.257265Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f296d16-5f56-449e-92bf-3136678bac45 · inbound

ReasoningGuard: Safeguarding Large Reasoning Models with Inference-time Safety Aha Moments cites this paper.

ReasoningGuard: Safeguarding Large Reasoning Models with Inference-time Safety Aha Moments Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibration

Reference 48

Resolution: verified exact; arxiv_id, observed 2026-05-19T01:02:54.880194Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation ca10b16b-864f-4190-a90d-f7279d962d68 · inbound

What Makes Position Zero Special? A Mechanistic Study of Position Zero Attention Sinks in LLMs cites this paper.

What Makes Position Zero Special? A Mechanistic Study of Position Zero Attention Sinks in LLMs Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibration

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-04T06:15:45.793248Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb695bea-f17b-4cd1-8ec2-1c15b83eab5b · inbound

When Sinks Help or Hurt: Unified Framework for Attention Sink in Large Vision-Language Models cites this paper.

When Sinks Help or Hurt: Unified Framework for Attention Sink in Large Vision-Language Models Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibration

Reference 45

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T23:23:26.789469Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation f2ac77db-d179-4f51-b2cb-579a0943a951 · inbound

When Sinks Help or Hurt: Unified Framework for Attention Sink in Large Vision-Language Models cites this paper.

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-02T17:04:25.869964Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5e37c56-c7c1-4aa3-b5e2-e3dbe75093e3 · inbound

Saliency-R1: Enforcing Interpretable and Faithful Vision-language Reasoning via Saliency-map Alignment Reward cites this paper.

Saliency-R1: Enforcing Interpretable and Faithful Vision-language Reasoning via Saliency-map Alignment Reward Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibration

Reference 87

Resolution: verified exact; arxiv_id, observed 2026-05-10T22:20:47.841443Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation ed7832ed-b4d2-4add-9227-c9488f9d8e30 · inbound

HyperLens: Quantifying Cognitive Effort in LLMs with Fine-grained Confidence Trajectory cites this paper.

HyperLens: Quantifying Cognitive Effort in LLMs with Fine-grained Confidence Trajectory Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibration

Reference 10

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T19:36:10.385501Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 6ab08144-e77a-41c8-ad1a-0cef9f43c5f7 · inbound

MLLMs Know When Before Speaking: Revealing and Recovering Temporal Grounding via Attention Cues cites this paper.

MLLMs Know When Before Speaking: Revealing and Recovering Temporal Grounding via Attention Cues Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibration

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-05-22T07:14:42.391167Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 1d687344-50de-4709-878f-ce935f0f5f5e · inbound

OccamToken: Efficient VLM Inference with Training-Free and Budget-Adaptive Token Pruning cites this paper.

OccamToken: Efficient VLM Inference with Training-Free and Budget-Adaptive Token Pruning Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibration

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-06-29T08:53:16.164258Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 1b64c4fd-23a8-4368-a378-a1fdb94a8a8c · inbound

Contribution Weights: A Geometrical Analysis of Self-Attention Transformers cites this paper.

Contribution Weights: A Geometrical Analysis of Self-Attention Transformers Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibration

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-06-28T23:32:46.662503Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.