Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy | Paper Citation Record

Observation 5addce12-de5d-4551-b6fd-3a5fb7e36ef2 · outbound

This paper cites 2025 , pages =.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy 2025 , pages =

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.318495Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 50bad945-8ea6-4d02-887f-3e3c34d27c35 · outbound

This paper cites Advances in Neural Information Processing Systems , volume =.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy Advances in Neural Information Processing Systems , volume =

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.398625Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 39d2979b-1e1d-4f66-903e-b7a90ba0f2e6 · outbound

This paper cites The Twelfth International Conference on Learning Representations , year =.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy The Twelfth International Conference on Learning Representations , year =

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.457717Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 4cffa676-7f1c-4001-bb1c-7761a4dbf32c · outbound

This paper cites LLaVA-NeXT: Improved reasoning, OCR, and world knowledge , url=.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy LLaVA-NeXT: Improved reasoning, OCR, and world knowledge , url=

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.403057Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 8d9df3d1-6fc3-4a3d-86b2-a613c44266b5 · outbound

This paper cites The Thirteenth International Conference on Learning Representations , year =.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy The Thirteenth International Conference on Learning Representations , year =

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.332235Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 91bfb8b9-9a69-4a26-ada7-207a33415392 · outbound

This paper cites The Twelfth International Conference on Learning Representations , year =.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy The Twelfth International Conference on Learning Representations , year =

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.334062Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 2e3bf15f-ca86-4d88-a4c2-bb5e822fdfba · outbound

This paper cites Proceedings of the.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy Proceedings of the

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.339443Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 935e1f9a-8d0d-40c9-ba8b-74159cd77a5d · outbound

This paper cites Advances in Neural Information Processing Systems , volume =.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy Advances in Neural Information Processing Systems , volume =

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.345504Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation ed004046-de83-44bd-8694-ee70e2e8e32c · outbound

This paper cites Proceedings of the.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy Proceedings of the

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.380981Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 8287beee-582c-4b5c-9ca9-61b5e622433e · outbound

This paper cites and Stepputtis, Simon and Morency, Louis-Philippe and Ramanan, Deva and Sycara, Katia and Xie, Yaqi , booktitle=.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy and Stepputtis, Simon and Morency, Louis-Philippe and Ramanan, Deva and Sycara, Katia and Xie, Yaqi , booktitle=

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.335677Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 78a339ed-f7ec-4aed-8638-f92a3b06067b · outbound

This paper cites Proceedings of the.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy Proceedings of the

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.322218Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 504e346c-dade-463c-935e-148dc1f7469b · outbound

This paper cites Proceedings of the 42nd International Conference on Machine Learning , pages =.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy Proceedings of the 42nd International Conference on Machine Learning , pages =

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.434620Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 1980b34f-26d1-4a36-9d6a-59643052af80 · outbound

This paper cites Cracking the Code of Hallucination in LVLMs with Vision-aware Head Divergence , booktitle =.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy Cracking the Code of Hallucination in LVLMs with Vision-aware Head Divergence , booktitle =

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.418525Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 66b26d5f-def2-4633-bf10-01d09e6063d6 · outbound

This paper cites Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition , pages=

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.395109Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation cb297a53-8c2d-453f-8378-d3aea84aa0c4 · outbound

This paper cites Steering LVLM s via Sparse Autoencoder for Hallucination Mitigation.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy Steering LVLM s via Sparse Autoencoder for Hallucination Mitigation

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.391041Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation ab399c63-0588-4300-8910-ca7ee4fd7b33 · outbound

This paper cites The Thirteenth International Conference on Learning Representations , year=.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy The Thirteenth International Conference on Learning Representations , year=

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.388972Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 5211e989-f6b6-42b7-a49b-befae56d8a76 · outbound

This paper cites Science China Information Sciences , volume =.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy Science China Information Sciences , volume =

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.400649Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation e5797cd2-9d7e-4ffa-a075-05597709da91 · outbound

This paper cites Shallow Focus, Deep Fixes: Enhancing Shallow Layers Vision Attention Sinks to Alleviate Hallucination in LVLM s.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy Shallow Focus, Deep Fixes: Enhancing Shallow Layers Vision Attention Sinks to Alleviate Hallucination in LVLM s

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.451785Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 72fbf803-3074-475f-9908-80cc27541cc0 · outbound

This paper cites Self-Introspective Decoding: Alleviating Hallucinations for Large Vision-Language Models , year =.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy Self-Introspective Decoding: Alleviating Hallucinations for Large Vision-Language Models , year =

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.371506Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation ffaedc10-4729-4c95-8696-da771b018882 · outbound

This paper cites Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding , pages=.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding , pages=

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.373490Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 6dddc3dc-745e-436d-b0d0-78e81dc29974 · outbound

This paper cites VQAG uider: Guiding Multimodal Large Language Models to Answer Complex Video Questions.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy VQAG uider: Guiding Multimodal Large Language Models to Answer Complex Video Questions

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.396981Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 1391780a-ca82-4ed9-b8c5-6f2414782cd9 · outbound

This paper cites Grounding Multimodal Large Language Models to the World , year =.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy Grounding Multimodal Large Language Models to the World , year =

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.442741Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 53b95153-fce4-4fc0-8feb-4d1ea4970e49 · outbound

This paper cites Proceedings of the IEEE/CVF International Conference on Computer Vision , pages=.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy Proceedings of the IEEE/CVF International Conference on Computer Vision , pages=

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.367467Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 790534c1-189e-431f-b124-2e97265eddd2 · outbound

This paper cites Object Hallucination in Image Captioning.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy Object Hallucination in Image Captioning

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.429067Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 0b4e52e8-0972-47b0-9d19-40025a99f77b · outbound

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

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy Evaluating Object Hallucination in Large Vision-Language Models

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.426580Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 6e538687-242c-4fc7-9f21-6ea76a28a7dd · outbound

This paper cites Aligning Large Multimodal Models with Factually Augmented RLHF.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy Aligning Large Multimodal Models with Factually Augmented RLHF

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.365702Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 81e10910-ea46-47d1-b38c-de0cca28abc8 · outbound

This paper cites Improved Baselines with Visual Instruction Tuning , pages=.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy Improved Baselines with Visual Instruction Tuning , pages=

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.369661Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation b70591cb-b77f-46c8-9ab1-d9298cf6aa43 · outbound

This paper cites Lawrence.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy Lawrence

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.377395Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 9397b85a-edb2-4fea-9b14-331e482f5fb7 · outbound

This paper cites 2022 , booktitle =.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy 2022 , booktitle =

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.337843Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 4471b5f8-30fb-4bb3-b656-fd2bbdad13f7 · outbound

This paper cites and Manning, Christopher D.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy and Manning, Christopher D

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.359523Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation bd4d8531-5ef8-43d2-ae14-176f7aafa71f · outbound

This paper cites Proceedings of the Thirty-Ninth.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy Proceedings of the Thirty-Ninth

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.361171Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 3092540f-5dfb-48bc-ad2f-acea838f65c4 · outbound

This paper cites DAMRO : Dive into the Attention Mechanism of LVLM to Reduce Object Hallucination.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy DAMRO : Dive into the Attention Mechanism of LVLM to Reduce Object Hallucination

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.363807Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation c305203f-7bbf-4694-98ca-c8e000649096 · outbound

This paper cites Proceedings of the 42nd International Conference on Machine Learning , volume =.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy Proceedings of the 42nd International Conference on Machine Learning , volume =

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.379271Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation e3ae1760-548c-4bfc-9cf1-3d6836fea397 · outbound

This paper cites I mage I n W ords: Unlocking Hyper-Detailed Image Descriptions.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy I mage I n W ords: Unlocking Hyper-Detailed Image Descriptions

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.440783Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation faad4691-b282-4b5a-8146-cb5f2cd13068 · outbound

This paper cites and Petryk, Suzanne and Gonzalez, Joseph E.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy and Petryk, Suzanne and Gonzalez, Joseph E

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.383378Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation e903a601-5fca-40c4-8797-0e5b086497e3 · outbound

This paper cites and Kachinthaya, Anish and Zou, Haodi and Canny, John and Gonzalez, Joseph E.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy and Kachinthaya, Anish and Zou, Haodi and Canny, John and Gonzalez, Joseph E

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.341665Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation d2de85e2-1b1a-4a2d-b1d1-9b204fbcd16f · outbound

This paper cites Proceedings of the Fortieth.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy Proceedings of the Fortieth

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.353491Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation cdda3410-c3f5-4d45-b264-f44f57783833 · outbound

This paper cites Mitigating object hallucinations in large vision-language models with assembly of global and local attention.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy Mitigating object hallucinations in large vision-language models with assembly of global and local attention

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.355134Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 89fb5d30-e96e-41f6-a8d6-113fa2008dfb · outbound

This paper cites Qwen3-VL Technical Report.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy Qwen3-VL Technical Report

Reference 46

Resolution: verified exact; local_arxiv, observed 2026-05-21T05:03:57.748585Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation b0cc244c-5a35-4b54-b35e-a4de574eeab6 · outbound

This paper cites M., Petryk, S., Gonzalez, J.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy M., Petryk, S., Gonzalez, J

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.349350Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation b2157b1c-65b9-4d55-9171-ecf14829c648 · outbound

This paper cites VQAG uider: Guiding multimodal large language models to answer complex video questions.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy VQAG uider: Guiding multimodal large language models to answer complex video questions

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.351014Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation c398ac7f-a14b-4893-b0fc-dea7ba50ad6e · outbound

This paper cites Alphaedit: Null-space constrained knowledge editing for language models.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy Alphaedit: Null-space constrained knowledge editing for language models

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.347169Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 4126e6e4-216b-4dff-8482-0cfaa9c1e668 · outbound

This paper cites MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models

Reference 50

Resolution: verified exact; local_arxiv, observed 2026-05-21T05:03:57.738260Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 70f5342e-0676-404a-a140-4610b69f09dc · outbound

This paper cites M., and Soricut, R.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy M., and Soricut, R

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.357503Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 28f55735-5886-422e-b163-3ce57e23dba3 · outbound

This paper cites DAMRO : Dive into the attention mechanism of LVLM to reduce object hallucination.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy DAMRO : Dive into the attention mechanism of LVLM to reduce object hallucination

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.385178Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation e1f86604-f1f5-4c7e-bc5f-d6422986d9d5 · outbound

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

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy Cracking the code of hallucination in lvlms with vision-aware head divergence

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.343307Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation d23ccd14-82a8-45b2-be05-8a760429e054 · outbound

This paper cites Steering LVLM s via sparse autoencoder for hallucination mitigation.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy Steering LVLM s via sparse autoencoder for hallucination mitigation

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.387306Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation a95b11c6-4557-4ec7-a21f-4e5805f217c1 · outbound

This paper cites Medical mllm is vulnerable: cross-modality jailbreak and mismatched attacks on medical multimodal large language models.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy Medical mllm is vulnerable: cross-modality jailbreak and mismatched attacks on medical multimodal large language models

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.324582Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation e6a8e62e-319c-4340-aa9e-363ae9b81953 · outbound

This paper cites Self-introspective decoding: Alleviating hallucinations for large vision-language models.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy Self-introspective decoding: Alleviating hallucinations for large vision-language models

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.328425Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation d33e5ccc-2979-4a59-a55b-20b74ef2d5e7 · outbound

This paper cites Visual attention never fades: Selective progressive attention recalibration for detailed image captioning in multimodal large language models.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy Visual attention never fades: Selective progressive attention recalibration for detailed image captioning in multimodal large language models

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.326282Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 21db0c55-76dc-4b0e-b73d-406381d4ca73 · outbound

This paper cites an unresolved cited work.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy Unresolved cited work

Reference 58

Resolution: unresolved; raw_fallback, observed 2026-05-21T05:03:58.329914Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation ccd35b3d-dd12-47bf-958a-3aa4ca362f3d · outbound

This paper cites an unresolved cited work.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy Unresolved cited work

Reference 59

Resolution: unresolved; raw_fallback, observed 2026-05-21T05:03:58.316984Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation d9c06841-2fa7-4a9f-a9fa-e3a3ae41fa2f · outbound

This paper cites Toward robust hyper-detailed image captioning: A multiagent approach and dual evaluation metrics for factuality and coverage.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy Toward robust hyper-detailed image captioning: A multiagent approach and dual evaluation metrics for factuality and coverage

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.453880Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 65f76eba-441a-43be-9a2a-dee7dbfb3447 · outbound

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

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy Mitigating object hallucinations in large vision-language models through visual contrastive decoding

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.448049Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 5611ff2c-db40-4053-9037-4c2a449532fa · outbound

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

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy Evaluating object hallucination in large vision-language models

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.446225Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 514cee3d-1ec6-41d6-8a00-4635478dd8ae · outbound

This paper cites an unresolved cited work.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy Unresolved cited work

Reference 63

Resolution: unresolved; raw_fallback, observed 2026-05-21T05:03:58.444294Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 2232bbb1-d5bc-45de-9302-1baac210546b · outbound

This paper cites an unresolved cited work.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy Unresolved cited work

Reference 64

Resolution: unresolved; raw_fallback, observed 2026-05-21T05:03:58.320541Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation b5ec508f-dde1-4cac-88a1-aa4d80316f42 · outbound

This paper cites an unresolved cited work.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy Unresolved cited work

Reference 65

Resolution: unresolved; raw_fallback, observed 2026-05-21T05:03:58.392435Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation f3f30ad8-af11-4550-b6ce-c53cbbb6a042 · outbound

This paper cites an unresolved cited work.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy Unresolved cited work

Reference 66

Resolution: unresolved; raw_fallback, observed 2026-05-21T05:03:58.450098Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation a119bb20-2032-438a-90eb-c3df165bebe5 · outbound

This paper cites A Survey on Hallucination in Large Vision-Language Models.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy A Survey on Hallucination in Large Vision-Language Models

Reference 67

Resolution: verified exact; local_arxiv, observed 2026-05-21T05:03:57.742123Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation a4f459f3-71a8-4f03-8744-af9db3515c86 · outbound

This paper cites Grounding multimodal large language models to the world.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy Grounding multimodal large language models to the world

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.438467Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation f493d763-1250-49de-b949-7206cd367d85 · outbound

This paper cites M., Kachinthaya, A., Zou, H., Canny, J., Gonzalez, J.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy M., Kachinthaya, A., Zou, H., Canny, J., Gonzalez, J

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.432476Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 4cd863a7-e8d8-4514-a740-1977e656f6b8 · outbound

This paper cites A., Burns, K., Darrell, T., and Saenko, K.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy A., Burns, K., Darrell, T., and Saenko, K

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.430537Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation d32622f5-ce42-4a56-a452-ac5d5edcf060 · outbound

This paper cites Aligning large multimodal models with factually augmented RLHF.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy Aligning large multimodal models with factually augmented RLHF

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.436788Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation fcaa1e07-ac44-4d02-96ed-b11f23810162 · outbound

This paper cites Seeing far and clearly: Mitigating hallucinations in mllms with attention causal decoding.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy Seeing far and clearly: Mitigating hallucinations in mllms with attention causal decoding

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.421893Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 95f92f49-2ca6-4105-808f-b2684e93a568 · outbound

This paper cites Q., Stepputtis, S., Morency, L.-P., Ramanan, D., Sycara, K., and Xie, Y.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy Q., Stepputtis, S., Morency, L.-P., Ramanan, D., Sycara, K., and Xie, Y

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.425527Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 92aa281a-8177-48dc-a630-c45c51970597 · outbound

This paper cites Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 74

Resolution: verified exact; local_arxiv, observed 2026-05-21T05:03:57.751902Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 16014604-876e-4b5f-80b8-b8a1dd9c0bd2 · outbound

This paper cites Caption Anything: Interactive Image Description with Diverse Multimodal Controls.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy Caption Anything: Interactive Image Description with Diverse Multimodal Controls

Reference 75

Resolution: metadata mismatch; arxiv_id, observed 2026-05-21T05:03:57.755094Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation d92bad9c-2be4-4b9a-9b6f-5ec1ec8371b9 · outbound

This paper cites ESMC: mllm-based embedding selection for explainable multiple clustering.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy ESMC: mllm-based embedding selection for explainable multiple clustering

Reference 76

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.414695Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 1f187497-832e-40ef-a976-584a7f91a835 · outbound

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

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy Clearsight: Visual signal enhancement for object hallucination mitigation in multimodal large language models

Reference 77

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.408584Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 402abc82-d652-49db-9f8d-9969e5da4902 · outbound

This paper cites Woodpecker: Hallucination correction for multimodal large language models.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy Woodpecker: Hallucination correction for multimodal large language models

Reference 78

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.406837Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 2492f909-13b7-4f33-801f-a7cc989d3a0f · outbound

This paper cites Rlhf-v: Towards trustworthy mllms via behavior alignment from fine-grained correctional human feedback.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy Rlhf-v: Towards trustworthy mllms via behavior alignment from fine-grained correctional human feedback

Reference 79

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.410824Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation fae9d251-beab-4c99-b0e6-3c941a492d8b · outbound

This paper cites Tell your model where to attend: Post-hoc attention steering for llms.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy Tell your model where to attend: Post-hoc attention steering for llms

Reference 80

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.412509Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 0834bdec-3428-4757-9062-a80d52918982 · outbound

This paper cites Vldrive: Vision-augmented lightweight mllms for efficient language-grounded autonomous driving.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy Vldrive: Vision-augmented lightweight mllms for efficient language-grounded autonomous driving

Reference 81

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.404765Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation e11059bf-75a1-4f27-815d-1a16835d44ed · outbound

This paper cites Shallow focus, deep fixes: Enhancing shallow layers vision attention sinks to alleviate hallucination in LVLM s.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy Shallow focus, deep fixes: Enhancing shallow layers vision attention sinks to alleviate hallucination in LVLM s

Reference 82

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.416394Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 6cb9b9ad-0d4b-4048-ae98-d22806a91254 · outbound

This paper cites Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization

Reference 83

Resolution: verified exact; local_arxiv, observed 2026-05-21T05:03:57.745343Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation 7236b3c1-60a3-4aa0-9d12-d3ca1e1cd61e · outbound

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

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy Minigpt-4: Enhancing vision-language understanding with advanced large language models

Reference 84

Resolution: verified fuzzy; raw_fallback, observed 2026-05-21T05:03:58.455987Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Observation ccc84fe3-98ea-44e5-ba62-fdd1d7bdd8e5 · outbound

This paper cites InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models.

Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

Reference 85

Resolution: verified exact; local_arxiv, observed 2026-05-21T05:03:57.759989Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers