Paper Citation Record · LEDGER

VCE: A zero-cost hallucination mitigation method of LVLMs via visual contrastive editing

As of 16 August 2026, this Paper Citation Record lists 27 of 27 outbound references and 1 inbound Pith citation observation for arXiv:2604.19412.

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

pith.paper-citation-record.v1
2604.19412 v1

Coverage vector

measured 27 of 27 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-10T03:16:45.483553Z

measured 28 of 28 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-16T06:30:59.297886+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-10T03:16:45.483553Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-05-11T12:41:03.021975Z

Reference resolution

27 of 27 outbound references displayed

verified exact4
verified fuzzy19
unresolved2
parse uncertain0
malformed identifier1
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 7561834a-475c-4366-bd59-2feddbc445d8 · outbound

This paper cites VCE: A zero-cost hallucination mitigation method of LVLMs via visual contrastive editing.

VCE: A zero-cost hallucination mitigation method of LVLMs via visual contrastive editing VCE: A zero-cost hallucination mitigation method of LVLMs via visual contrastive editing

Reference 1

Resolution: metadata mismatch; local_arxiv, observed 2026-05-11T12:41:03.027938Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 5f5bc6f0-68ec-4a0b-82f7-d12588e474c7 · outbound

This paper cites an unresolved cited work.

VCE: A zero-cost hallucination mitigation method of LVLMs via visual contrastive editing Unresolved cited work

Reference 2

Resolution: unresolved; raw_fallback, observed 2026-05-22T17:16:51.263512Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation a5be9d33-3cc9-4e3f-8879-1a610eb1d980 · outbound

This paper cites Problem Definition Mathematically, an LVLM can be defined as a conditional probability distribution: p(y|x,v;θ) = TY t=1 pθ yt |y <t,x,v ,(1) wherey={y 1, y2.

VCE: A zero-cost hallucination mitigation method of LVLMs via visual contrastive editing Problem Definition Mathematically, an LVLM can be defined as a conditional probability distribution: p(y|x,v;θ) = TY t=1 pθ yt |y <t,x,v ,(1) wherey={y 1, y2

Reference 3

Resolution: malformed identifier; raw_fallback, observed 2026-05-22T17:16:51.269515Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 13dbed42-0e8a-4a1b-8d0b-ebe4200a1c48 · outbound

This paper cites Experiment Setups Datasets.We evaluate the VCE method on popular hallucina- tion benchmarks: POPE [18] and CHAIR [19].

VCE: A zero-cost hallucination mitigation method of LVLMs via visual contrastive editing Experiment Setups Datasets.We evaluate the VCE method on popular hallucina- tion benchmarks: POPE [18] and CHAIR [19]

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:16:51.266506Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 2369eac1-6aa4-487b-80b0-a13cc11c85f3 · outbound

This paper cites an unresolved cited work.

VCE: A zero-cost hallucination mitigation method of LVLMs via visual contrastive editing Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-05-22T17:16:51.325352Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 23a44f56-fffd-44fe-978a-1f352aa1b228 · outbound

This paper cites Ai flow: Perspectives, scenarios, and ap- proaches.

VCE: A zero-cost hallucination mitigation method of LVLMs via visual contrastive editing Ai flow: Perspectives, scenarios, and ap- proaches

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:16:51.328555Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation fe7c2518-df9d-4540-8a06-26d3b0bcc1ee · outbound

This paper cites Transfer metric learning: algorithms, ap- plications and outlooks.

VCE: A zero-cost hallucination mitigation method of LVLMs via visual contrastive editing Transfer metric learning: algorithms, ap- plications and outlooks

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:16:51.331187Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation e791e6f1-0b9b-4049-bb04-92271c782f2c · outbound

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

VCE: A zero-cost hallucination mitigation method of LVLMs via visual contrastive editing Evaluating object hallucination in large vision-language models

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:16:51.309472Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 846dd7f7-1b90-4464-8088-c56dfe4c37c6 · outbound

This paper cites Prompt injection attacks on vision language models in oncology.

VCE: A zero-cost hallucination mitigation method of LVLMs via visual contrastive editing Prompt injection attacks on vision language models in oncology

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:16:51.312888Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation f27317ff-78b8-4094-b1fc-bcb62436d8c2 · outbound

This paper cites Towards attack models in autonomous systems of systems.

VCE: A zero-cost hallucination mitigation method of LVLMs via visual contrastive editing Towards attack models in autonomous systems of systems

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:16:51.316656Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation f6fb7c2a-dc77-4155-baa5-2a578426d52c · outbound

This paper cites Hallucination mitigation for retrieval-augmented large language models: A review.

VCE: A zero-cost hallucination mitigation method of LVLMs via visual contrastive editing Hallucination mitigation for retrieval-augmented large language models: A review

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:16:51.319772Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 7bcc852d-f1f2-4131-a18c-5f45e191f15a · outbound

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

VCE: A zero-cost hallucination mitigation method of LVLMs via visual contrastive editing Opera: Al- leviating hallucination in multi-modal large language models via over-trust penalty and retrospection-allocation

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:16:51.322778Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 63d78635-2af5-4eac-9ff7-0cf12b2e329e · outbound

This paper cites Truthprint: Miti- gating lvlm object hallucination via latent truthful-guided pre- intervention.

VCE: A zero-cost hallucination mitigation method of LVLMs via visual contrastive editing Truthprint: Miti- gating lvlm object hallucination via latent truthful-guided pre- intervention

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-11T12:41:02.987352Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ccb4359a-1908-40c6-a8a9-0757ec99aa16 · outbound

This paper cites Woodpecker: Hallucination correction for multimodal large language mod- els.

VCE: A zero-cost hallucination mitigation method of LVLMs via visual contrastive editing Woodpecker: Hallucination correction for multimodal large language mod- els

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:16:51.294747Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 075317f9-aa90-45e1-9faf-403a73326179 · outbound

This paper cites Alleviating hallucination in large vision- language models with active retrieval augmentation.

VCE: A zero-cost hallucination mitigation method of LVLMs via visual contrastive editing Alleviating hallucination in large vision- language models with active retrieval augmentation

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:16:51.298287Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ed48cb7b-9547-43c8-a956-38305bb875d7 · outbound

This paper cites Look, compare, decide: Alleviating hallucination in large vision-language models via multi-view multi-path reasoning.

VCE: A zero-cost hallucination mitigation method of LVLMs via visual contrastive editing Look, compare, decide: Alleviating hallucination in large vision-language models via multi-view multi-path reasoning

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:16:51.291548Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation e2e724c8-a978-4aec-ac97-9634080df089 · outbound

This paper cites Mitigating Multilingual Hallucination in Large Vision-Language Models.

VCE: A zero-cost hallucination mitigation method of LVLMs via visual contrastive editing Mitigating Multilingual Hallucination in Large Vision-Language Models

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-11T12:41:03.018048Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation eaf5175a-dd19-4417-855e-80bd8f25d913 · outbound

This paper cites Analyzing and Mitigating Object Hallucination in Large Vision-Language Models.

VCE: A zero-cost hallucination mitigation method of LVLMs via visual contrastive editing Analyzing and Mitigating Object Hallucination in Large Vision-Language Models

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-17T22:46:52.958092Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 7050b9f7-ab68-4eff-8bfa-64f899aa2713 · outbound

This paper cites Dola: Decoding by contrasting layers improves factuality in large language mod- els.

VCE: A zero-cost hallucination mitigation method of LVLMs via visual contrastive editing Dola: Decoding by contrasting layers improves factuality in large language mod- els

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:16:51.278280Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation e3a4a9d5-d6bb-4005-b721-d0b0193f8f90 · outbound

This paper cites OPERA: alleviating hallucination in multi-modal large language mod- els via over-trust penalty and retrospection-allocation.

VCE: A zero-cost hallucination mitigation method of LVLMs via visual contrastive editing OPERA: alleviating hallucination in multi-modal large language mod- els via over-trust penalty and retrospection-allocation

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:16:51.284625Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation aae08888-6c8a-43fe-84f1-98476c56a141 · outbound

This paper cites Mit- igating object hallucinations in large vision-language mod- els through visual contrastive decoding.

VCE: A zero-cost hallucination mitigation method of LVLMs via visual contrastive editing Mit- igating object hallucinations in large vision-language mod- els through visual contrastive decoding

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:16:51.272514Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d47afba3-eb47-4063-bdef-18dd605367bb · outbound

This paper cites Denoising dif- fusion probabilistic models.

VCE: A zero-cost hallucination mitigation method of LVLMs via visual contrastive editing Denoising dif- fusion probabilistic models

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:16:51.305911Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 6985e4a8-ea3c-4937-8a6e-d68b72d86e3b · outbound

This paper cites Evaluating Object Hallucination in Large Vision-Language Models.

VCE: A zero-cost hallucination mitigation method of LVLMs via visual contrastive editing Evaluating Object Hallucination in Large Vision-Language Models

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-11T13:44:10.072171Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 03c406fa-1b16-4c25-9e7b-d436289300d1 · outbound

This paper cites Object hallucination in image cap- tioning.

VCE: A zero-cost hallucination mitigation method of LVLMs via visual contrastive editing Object hallucination in image cap- tioning

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:16:51.274992Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ffe0272e-54c5-4a49-9e50-bcca177cf6c0 · outbound

This paper cites Im- proved baselines with visual instruction tuning.

VCE: A zero-cost hallucination mitigation method of LVLMs via visual contrastive editing Im- proved baselines with visual instruction tuning

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:16:51.281594Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation aac285ed-477f-49b3-b69e-b1fad1280117 · outbound

This paper cites Minigpt-4: Enhancing vision-language understanding with advanced large language models.

VCE: A zero-cost hallucination mitigation method of LVLMs via visual contrastive editing Minigpt-4: Enhancing vision-language understanding with advanced large language models

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:16:51.287992Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 9b33b356-efef-45c6-ac2c-56b34d3374eb · outbound

This paper cites mplug-owl2: Rev- olutionizing multi-modal large language model with modal- ity collaboration.

VCE: A zero-cost hallucination mitigation method of LVLMs via visual contrastive editing mplug-owl2: Rev- olutionizing multi-modal large language model with modal- ity collaboration

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-05-22T17:16:51.301670Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Pith citing papers

Observation 7561834a-475c-4366-bd59-2feddbc445d8 · inbound