Paper Citation Record · LEDGER

Tell Model Where to Look: Mitigating Hallucinations in MLLMs by Vision-Guided Attention

As of 4 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 4 inbound Pith citation observations for arXiv:2511.20032.

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

pith.paper-citation-record.v1
2511.20032 v3

Coverage vector

measured 37 of 37 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-17T04:57:59.837094Z

measured 41 of 41 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 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-02T23:33:16.095675Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-02T12:46:56.634866Z

Reference resolution

37 of 37 outbound references displayed

verified exact6
verified fuzzy30
unresolved0
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 1e2942f0-dedd-4b74-bdbe-48baf864aa97 · outbound

This paper cites Qwen2.5-VL Technical Report.

Tell Model Where to Look: Mitigating Hallucinations in MLLMs by Vision-Guided Attention Qwen2.5-VL Technical Report

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-05-17T04:59:03.943257Z

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 64cf7382-21bb-487e-8ce0-761480506c13 · outbound

This paper cites Per- turbollava: Reducing multimodal hallucinations with pertur- bative visual training.

Tell Model Where to Look: Mitigating Hallucinations in MLLMs by Vision-Guided Attention Per- turbollava: Reducing multimodal hallucinations with pertur- bative visual training

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T04:59:04.599961Z

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 f5ac82f3-9d6e-42cb-b014-69ad224d2a8f · outbound

This paper cites Why is spatial reasoning hard for vlms? an attention mechanism perspective on focus areas.

Tell Model Where to Look: Mitigating Hallucinations in MLLMs by Vision-Guided Attention Why is spatial reasoning hard for vlms? an attention mechanism perspective on focus areas

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T04:59:04.602830Z

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 ef71d9a8-58f0-424d-9dd8-46e4b36be0d7 · outbound

This paper cites Flashattention: Fast and memory-efficient exact at- tention with io-awareness.

Tell Model Where to Look: Mitigating Hallucinations in MLLMs by Vision-Guided Attention Flashattention: Fast and memory-efficient exact at- tention with io-awareness

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T04:59:04.589035Z

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 28751829-d90b-465a-a9e3-361d4242be7f · outbound

This paper cites Cracking the code of hallucination in lvlms with vision-aware head divergence.

Tell Model Where to Look: Mitigating Hallucinations in MLLMs by Vision-Guided Attention Cracking the code of hallucination in lvlms with vision-aware head divergence

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T04:59:04.580395Z

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 b3c374af-cb7f-4981-9b2f-53d8d014ef53 · outbound

This paper cites Opera: Alleviating hallucination in multi- modal large language models via over-trust penalty and retrospection-allocation.

Tell Model Where to Look: Mitigating Hallucinations in MLLMs by Vision-Guided Attention Opera: Alleviating hallucination in multi- modal large language models via over-trust penalty and retrospection-allocation

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T04:59:04.583360Z

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 de05ee4b-4067-4ba3-be84-4ddb209ef486 · outbound

This paper cites Interpreting and editing vision-language representations to mitigate hallucinations.

Tell Model Where to Look: Mitigating Hallucinations in MLLMs by Vision-Guided Attention Interpreting and editing vision-language representations to mitigate hallucinations

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T04:59:04.591870Z

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 00e02cf0-9c91-41a2-a255-59b4d9a11d90 · outbound

This paper cites See what you are told: Visual attention sink in large multimodal models.

Tell Model Where to Look: Mitigating Hallucinations in MLLMs by Vision-Guided Attention See what you are told: Visual attention sink in large multimodal models

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T04:59:04.597282Z

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 d56d0339-ac49-48b3-95b0-57c6a1aca440 · outbound

This paper cites Mitigating object hal- lucinations in large vision-language models through visual contrastive decoding.

Tell Model Where to Look: Mitigating Hallucinations in MLLMs by Vision-Guided Attention Mitigating object hal- lucinations in large vision-language models through visual contrastive decoding

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T04:59:04.577422Z

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 24c4ac0a-195e-42be-bb8a-7190c3105699 · outbound

This paper cites Treble counterfactual vlms: A causal approach to hallucination.

Tell Model Where to Look: Mitigating Hallucinations in MLLMs by Vision-Guided Attention Treble counterfactual vlms: A causal approach to hallucination

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T04:59:04.586157Z

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 7d894311-e9f5-4568-a602-4dd54c9a5d95 · outbound

This paper cites Evaluating object hallucination in large vision-language models.

Tell Model Where to Look: Mitigating Hallucinations in MLLMs by Vision-Guided Attention Evaluating object hallucination in large vision-language models

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T04:59:04.568353Z

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 e2a7999e-bcf0-400d-9d92-9a9494fd18b9 · outbound

This paper cites The hidden life of tokens: Reducing hallucination of large vision-language models via visual in- formation steering.

Tell Model Where to Look: Mitigating Hallucinations in MLLMs by Vision-Guided Attention The hidden life of tokens: Reducing hallucination of large vision-language models via visual in- formation steering

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T04:59:04.574394Z

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 220c7cbf-3945-4868-8ce7-b98f962baab7 · outbound

This paper cites Microsoft coco: Common objects in context.

Tell Model Where to Look: Mitigating Hallucinations in MLLMs by Vision-Guided Attention Microsoft coco: Common objects in context

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T04:59:04.571365Z

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 61955323-7b52-40bf-ad4b-ac6e49dd5b8a · outbound

This paper cites Improved baselines with visual instruction tuning.

Tell Model Where to Look: Mitigating Hallucinations in MLLMs by Vision-Guided Attention Improved baselines with visual instruction tuning

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T04:59:04.594481Z

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 60e3dce2-547c-455e-b964-dbd3e2c681d1 · outbound

This paper cites Llava-next: Im- proved reasoning, ocr, and world knowledge.

Tell Model Where to Look: Mitigating Hallucinations in MLLMs by Vision-Guided Attention Llava-next: Im- proved reasoning, ocr, and world knowledge

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T04:59:04.606025Z

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 8d15d819-ebe9-409d-af06-9bb069a448b8 · outbound

This paper cites Paying more at- tention to image: A training-free method for alleviating hal- lucination in lvlms.

Tell Model Where to Look: Mitigating Hallucinations in MLLMs by Vision-Guided Attention Paying more at- tention to image: A training-free method for alleviating hal- lucination in lvlms

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T04:59:04.565437Z

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 28ee871c-c11c-4ca6-8f6c-da0c583920ae · outbound

This paper cites Mitigating hallucination through theory-consistent symmetric multimodal preference optimization.

Tell Model Where to Look: Mitigating Hallucinations in MLLMs by Vision-Guided Attention Mitigating hallucination through theory-consistent symmetric multimodal preference optimization

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-17T04:59:03.924426Z

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 4a467014-6d47-401f-a7b5-6011de4a5f25 · outbound

This paper cites Second: Mitigating perceptual hallucination in vision- language models via selective and contrastive decoding.

Tell Model Where to Look: Mitigating Hallucinations in MLLMs by Vision-Guided Attention Second: Mitigating perceptual hallucination in vision- language models via selective and contrastive decoding

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T04:59:04.556498Z

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 e73dff2d-61e6-4c51-b099-475b64998976 · outbound

This paper cites Stanza: A python natural language processing toolkit for many human languages.

Tell Model Where to Look: Mitigating Hallucinations in MLLMs by Vision-Guided Attention Stanza: A python natural language processing toolkit for many human languages

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T04:59:04.546708Z

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 0ab666fb-9148-4993-989d-697d2f94bd89 · outbound

This paper cites Object hallucination in image cap- tioning.

Tell Model Where to Look: Mitigating Hallucinations in MLLMs by Vision-Guided Attention Object hallucination in image cap- tioning

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T04:59:04.553379Z

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 175effb1-4b33-4c7b-b297-6b8c0ceb7ca7 · outbound

This paper cites Mitigating ob- ject hallucination in mllms via data-augmented phrase-level alignment.

Tell Model Where to Look: Mitigating Hallucinations in MLLMs by Vision-Guided Attention Mitigating ob- ject hallucination in mllms via data-augmented phrase-level alignment

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T04:59:04.543532Z

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 3a6c6808-7b3e-488e-b724-536632b5001d · outbound

This paper cites AMBER: An LLM-free Multi-dimensional Benchmark for MLLMs Hallucination Evaluation.

Tell Model Where to Look: Mitigating Hallucinations in MLLMs by Vision-Guided Attention AMBER: An LLM-free Multi-dimensional Benchmark for MLLMs Hallucination Evaluation

Reference 22

Resolution: verified exact; local_arxiv, observed 2026-05-17T04:59:03.939203Z

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 3a75a718-d55f-4de1-851f-cde76af95676 · outbound

This paper cites Damo: Decoding by accumulating activations mo- mentum for mitigating hallucinations in vision-language models.

Tell Model Where to Look: Mitigating Hallucinations in MLLMs by Vision-Guided Attention Damo: Decoding by accumulating activations mo- mentum for mitigating hallucinations in vision-language models

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T04:59:04.550045Z

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 063c6488-ec1d-4eb1-bbb8-743809c56075 · outbound

This paper cites Detecting and mitigating hallucination in large vi- sion language models via fine-grained ai feedback.

Tell Model Where to Look: Mitigating Hallucinations in MLLMs by Vision-Guided Attention Detecting and mitigating hallucination in large vi- sion language models via fine-grained ai feedback

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T04:59:04.559590Z

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 05bd781f-5a76-4054-8492-9a0eadfd7133 · outbound

This paper cites TARAC: Mitigating Hallucination in LVLMs via Temporal Attention Real-time Accumulative Connection.

Tell Model Where to Look: Mitigating Hallucinations in MLLMs by Vision-Guided Attention TARAC: Mitigating Hallucination in LVLMs via Temporal Attention Real-time Accumulative Connection

Reference 25

Resolution: verified exact; local_arxiv, observed 2026-05-17T04:59:03.947695Z

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 07ca6d34-7679-4ec9-a3c2-f54bd28a7e99 · outbound

This paper cites Un- derstanding and mitigating hallucination in large vision- language models via modular attribution and intervention.

Tell Model Where to Look: Mitigating Hallucinations in MLLMs by Vision-Guided Attention Un- derstanding and mitigating hallucination in large vision- language models via modular attribution and intervention

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T04:59:04.540043Z

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 1549e680-a5b8-467e-848e-d9f8a3fccc04 · outbound

This paper cites Clearsight: visual signal enhancement for object hallucination mitigation in multimodal large language models.

Tell Model Where to Look: Mitigating Hallucinations in MLLMs by Vision-Guided Attention Clearsight: visual signal enhancement for object hallucination mitigation in multimodal large language models

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T04:59:04.536068Z

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 a39d53db-e30c-47a9-a05a-2f5496ee4b63 · outbound

This paper cites Lifting the veil on visual information flow in mllms: Unlocking pathways to faster inference.

Tell Model Where to Look: Mitigating Hallucinations in MLLMs by Vision-Guided Attention Lifting the veil on visual information flow in mllms: Unlocking pathways to faster inference

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T04:59:04.532067Z

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 69d686a6-33e2-4e1e-88c1-e105a0370b74 · outbound

This paper cites Woodpecker: Hallucination correction for multimodal large language models.Science China Information Sciences, 67(12):220105.

Tell Model Where to Look: Mitigating Hallucinations in MLLMs by Vision-Guided Attention Woodpecker: Hallucination correction for multimodal large language models.Science China Information Sciences, 67(12):220105

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T04:59:04.520514Z

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 6e4e3eb8-dee3-4ef3-bb26-c7e81946f282 · outbound

This paper cites Self- correcting decoding with generative feedback for mitigating hallucinations in large vision-language models.

Tell Model Where to Look: Mitigating Hallucinations in MLLMs by Vision-Guided Attention Self- correcting decoding with generative feedback for mitigating hallucinations in large vision-language models

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T04:59:04.524354Z

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 e18fd529-69e6-4987-bcf4-1616206d51d7 · outbound

This paper cites Cross-modal information flow in multimodal large language models.

Tell Model Where to Look: Mitigating Hallucinations in MLLMs by Vision-Guided Attention Cross-modal information flow in multimodal large language models

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T04:59:04.528176Z

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 b8cc7494-6ae7-4373-9821-61c3af417a30 · outbound

This paper cites Cross- image contrastive decoding: Precise, lossless suppression of language priors in large vision-language models.

Tell Model Where to Look: Mitigating Hallucinations in MLLMs by Vision-Guided Attention Cross- image contrastive decoding: Precise, lossless suppression of language priors in large vision-language models

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-05-17T04:59:03.934743Z

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 2a8a0232-2b5c-4309-9528-531825338f56 · outbound

This paper cites Align- ing attention distribution to information flow for hallucina- tion mitigation in large vision-language models.

Tell Model Where to Look: Mitigating Hallucinations in MLLMs by Vision-Guided Attention Align- ing attention distribution to information flow for hallucina- tion mitigation in large vision-language models

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T04:59:04.513481Z

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 ee9038c4-deb6-493b-a6db-c976d7bb05f4 · outbound

This paper cites Cross-layer vision smoothing: Enhancing visual understanding via sustained focus on key objects in large vision-language models.

Tell Model Where to Look: Mitigating Hallucinations in MLLMs by Vision-Guided Attention Cross-layer vision smoothing: Enhancing visual understanding via sustained focus on key objects in large vision-language models

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-05-17T04:59:03.929547Z

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 23c1efdc-3866-4516-ae2b-dcd57cebca86 · outbound

This paper cites Mitigating object hallucination in large vision-language models via image-grounded guidance.

Tell Model Where to Look: Mitigating Hallucinations in MLLMs by Vision-Guided Attention Mitigating object hallucination in large vision-language models via image-grounded guidance

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T04:59:04.516838Z

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 833987f2-e7aa-495d-9375-5647a3043954 · outbound

This paper cites Ibd: Alleviating hallucinations in large vision- language models via image-biased decoding.

Tell Model Where to Look: Mitigating Hallucinations in MLLMs by Vision-Guided Attention Ibd: Alleviating hallucinations in large vision- language models via image-biased decoding

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-05-17T04:59:04.510496Z

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 c875a36b-3b4f-43f8-9311-0dd1feb7d7a3 · outbound

This paper cites Look twice before you answer: Memory- space visual retracing for hallucination mitigation in multi- modal large language models.

Tell Model Where to Look: Mitigating Hallucinations in MLLMs by Vision-Guided Attention Look twice before you answer: Memory- space visual retracing for hallucination mitigation in multi- modal large language models

Reference 37

Resolution: malformed identifier; raw_fallback, observed 2026-05-17T04:59:04.562505Z

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 ed78946e-2ef0-4321-814d-3a54309d0d58 · inbound

SAVAA: Mitigating Hallucinations in LVLMs via Step-wise Adaptive Visual Attention Amplification cites this paper.

SAVAA: Mitigating Hallucinations in LVLMs via Step-wise Adaptive Visual Attention Amplification Tell Model Where to Look: Mitigating Hallucinations in MLLMs by Vision-Guided Attention

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-02T23:33:16.095675Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70ba121e-e0bd-4592-b597-c0ae3a14c80f · inbound

Mechanistic Insights into Functional Sparsity in Multimodal LLMs via CoRe Heads cites this paper.

Mechanistic Insights into Functional Sparsity in Multimodal LLMs via CoRe Heads Tell Model Where to Look: Mitigating Hallucinations in MLLMs by Vision-Guided Attention

Reference 30

Resolution: verified exact; local_arxiv, observed 2026-07-02T12:46:56.636468Z

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 f44f9a0d-8a60-45ba-a916-943ba087f423 · inbound

ADAPT: Attention Dynamics Alignment with Preference Tuning for Faithful MLLMs cites this paper.

ADAPT: Attention Dynamics Alignment with Preference Tuning for Faithful MLLMs Tell Model Where to Look: Mitigating Hallucinations in MLLMs by Vision-Guided Attention

Reference 41

Resolution: metadata mismatch; local_arxiv, observed 2026-07-01T06:55:29.470417Z

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 50ae2b93-7c8c-4879-8d9a-9b83a4aa3cf7 · inbound

Witness Evidence Portfolios: Single-Prefill Risk Detection for Closed Multimodal Answers cites this paper.

Witness Evidence Portfolios: Single-Prefill Risk Detection for Closed Multimodal Answers Tell Model Where to Look: Mitigating Hallucinations in MLLMs by Vision-Guided Attention

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-01T03:42:52.863425Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.