Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination | Paper Citation Record

Observation 0e320b62-8865-4ece-abad-63999b4708fd · outbound

This paper cites Flamingo: a visual language model for few-shot learning.Advances in neural information processing systems, 35:23716–23736,.

Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination Flamingo: a visual language model for few-shot learning.Advances in neural information processing systems, 35:23716–23736,

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-10T10:47:43.891133Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99d03d34-605b-4c96-9e6a-54551257cd88 · outbound

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

Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination Mitigating object hallucinations in large vision- language models with assembly of global and local attention

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T10:47:44.841598Z

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 f8ba24a2-c3c4-4151-a77a-6592f564fb22 · outbound

This paper cites Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond.

Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-10T10:47:43.900405Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82a7088a-e450-4fce-9278-68e97ad3d517 · outbound

This paper cites Hallucination of Multimodal Large Language Models: A Survey.

Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination Hallucination of Multimodal Large Language Models: A Survey

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-10T10:47:43.905091Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3cf3aa9d-e1d5-484b-9485-2e3fb0831961 · outbound

This paper cites Ict: Image-object cross-level trusted intervention for mitigating object halluci- nation in large vision-language models.

Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination Ict: Image-object cross-level trusted intervention for mitigating object halluci- nation in large vision-language models

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T10:47:44.830009Z

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 c151d0e4-ad30-4c36-9fc8-f3cbc4665155 · outbound

This paper cites Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic.

Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-10T10:47:43.914584Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7000a756-3aa0-4606-9338-7fc8a9f5274b · outbound

This paper cites Mitigating Hallucination in Visual Language Models with Visual Supervision.

Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination Mitigating Hallucination in Visual Language Models with Visual Supervision

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-10T10:47:43.918681Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b11a80a3-aaa8-412a-8a3a-176479ab9f85 · outbound

This paper cites Internvl: Scaling up vision foundation mod- els and aligning for generic visual-linguistic tasks.

Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination Internvl: Scaling up vision foundation mod- els and aligning for generic visual-linguistic tasks

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-10T10:47:43.922861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e89ab366-f85c-431a-8c3a-7467c7ac55c2 · outbound

This paper cites HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding.

Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-10T10:47:43.926644Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4dde930-0bf6-42af-87fb-bbe478075ca4 · outbound

This paper cites Instructblip: Towards general-purpose vision- language models with instruction tuning.Advances in neural information processing systems, 36:49250–49267, 2023.

Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination Instructblip: Towards general-purpose vision- language models with instruction tuning.Advances in neural information processing systems, 36:49250–49267, 2023

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-10T10:47:43.930595Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60cb3f27-032c-4303-8ea5-e7a8d8d689d4 · outbound

This paper cites Damro: Dive into the attention mechanism of lvlm to re- duce object hallucination.arXiv preprint arXiv:2410.04514,.

Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination Damro: Dive into the attention mechanism of lvlm to re- duce object hallucination.arXiv preprint arXiv:2410.04514,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-10T10:47:43.934722Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 86a2d1d9-cf6e-4cc0-962f-6032434cbb14 · outbound

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

Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination Opera: Alleviating hallucination in multi- modal large language models via over-trust penalty and retrospection-allocation

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T10:47:44.803823Z

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 00a1ab87-7705-4d79-bfc7-4bf232784739 · outbound

This paper cites Hallucination augmented contrastive learn- ing for multimodal large language model.

Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination Hallucination augmented contrastive learn- ing for multimodal large language model

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T10:47:44.791239Z

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 615a9787-1c90-4108-8fb9-c20c8e3c0411 · outbound

This paper cites Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations.

Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-10T10:47:43.945970Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fcda5f3b-5dad-45a7-b2c4-e0e8ca6eed1a · outbound

This paper cites Devils in middle layers of large vision- language models: Interpreting, detecting and mitigating ob- ject hallucinations via attention lens.

Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination Devils in middle layers of large vision- language models: Interpreting, detecting and mitigating ob- ject hallucinations via attention lens

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T10:47:44.780119Z

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 2dfebab3-5a67-4cf4-8e2f-57ef29db632b · outbound

This paper cites What’s in the im- age? a deep-dive into the vision of vision language models.

Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination What’s in the im- age? a deep-dive into the vision of vision language models

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T10:47:44.768877Z

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 bc3af201-0a87-4966-a990-2f6c2f8c9e5d · outbound

This paper cites See What You Are Told: Visual Attention Sink in Large Multimodal Models.

Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination See What You Are Told: Visual Attention Sink in Large Multimodal Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-10T10:47:43.957166Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2deb19e1-8498-4016-99bc-2ff7fe9c96b5 · outbound

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

Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination Mitigating object hal- lucinations in large vision-language models through visual contrastive decoding

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T10:47:44.756687Z

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 dee3fdc5-0835-45d7-971e-9ba4096b2e8a · outbound

This paper cites Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models.

Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-10T10:47:43.964835Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e31a5d3-4f45-4260-a211-e3fe9936d7b9 · outbound

This paper cites Mvbench: A comprehensive multi-modal video understand- ing benchmark.

Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination Mvbench: A comprehensive multi-modal video understand- ing benchmark

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-10T10:47:43.968690Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c87cbf62-5bc7-4ca1-a1b5-6d09e73ae0b9 · outbound

This paper cites Contrastive decoding: Open-ended text genera- tion as optimization.

Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination Contrastive decoding: Open-ended text genera- tion as optimization

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T10:47:44.731096Z

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 dcc333b6-e883-47d0-ab57-4aae01192727 · outbound

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

Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination Evaluating Object Hallucination in Large Vision-Language Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-10T10:47:43.975914Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eabe12cc-a553-4028-b6fd-31e4c2dd20f1 · outbound

This paper cites Microsoft coco: Common objects in context.

Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination Microsoft coco: Common objects in context

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-10T10:47:43.979840Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 887a82ea-f4bb-42a5-adde-1e19b3be83ff · outbound

This paper cites Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning.

Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-10T10:47:43.983427Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa1b95be-cf8f-4b06-bee2-bf17ed85f7a0 · outbound

This paper cites Visual instruction tuning.Advances in neural information processing systems, 36:34892–34916, 2023.

Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination Visual instruction tuning.Advances in neural information processing systems, 36:34892–34916, 2023

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-10T10:47:43.987399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab154c61-d930-40b6-8d2b-c4691ab32fa9 · outbound

This paper cites Improved baselines with visual instruction tuning.

Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination Improved baselines with visual instruction tuning

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T10:47:44.702842Z

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 e3ca8da4-6f46-4fb1-b164-22c40ec6631c · outbound

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

Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination A Survey on Hallucination in Large Vision-Language Models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-10T10:47:43.994864Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53c0377c-6c8c-43b3-9eef-9b2059253bd3 · outbound

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

Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination Paying more at- tention to image: A training-free method for alleviating hal- lucination in lvlms

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T10:47:44.689548Z

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 88eb18a9-d520-4dd6-9d9f-56240c02f130 · outbound

This paper cites Alleviating hallucinations in large vision- language models through hallucination-induced optimiza- tion.Advances in Neural Information Processing Systems, 37:122811–122832, 2024.

Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination Alleviating hallucinations in large vision- language models through hallucination-induced optimiza- tion.Advances in Neural Information Processing Systems, 37:122811–122832, 2024

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T10:47:44.676793Z

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 9f54d766-b08b-440c-9f24-7a90343b4901 · outbound

This paper cites Wordnet: a lexical database for english.

Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination Wordnet: a lexical database for english

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T10:47:44.664276Z

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 c721d87f-671f-40b3-b4d1-e4b82b481a6d · outbound

This paper cites Interpreting gpt: The logit lens.

Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination Interpreting gpt: The logit lens

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T10:47:44.653301Z

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 8790dd97-557f-4dd7-b86d-cdfdb9a45777 · outbound

This paper cites Learning transferable visual models from natural language supervi- sion.

Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination Learning transferable visual models from natural language supervi- sion

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-10T10:47:44.014328Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4768a1b-8578-41a1-89c9-2e7b3fa691ed · outbound

This paper cites Object Hallucination in Image Captioning.

Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination Object Hallucination in Image Captioning

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-10T10:47:44.018119Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44ff7873-12ee-4b4f-a979-a48396d2dd0a · outbound

This paper cites Mitigating Object Hallucination in MLLMs via Data-augmented Phrase-level Alignment.

Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination Mitigating Object Hallucination in MLLMs via Data-augmented Phrase-level Alignment

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-10T10:47:44.022178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db768d3b-9524-429e-b314-8d5741a8c656 · outbound

This paper cites Overconfidence in LLM-as-a-Judge: Diagnosis and Confidence-Driven Solution.

Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination Overconfidence in LLM-as-a-Judge: Diagnosis and Confidence-Driven Solution

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-10T10:47:44.026423Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6162e675-7f02-4ab3-8c82-3394dccfaeac · outbound

This paper cites Eyes wide shut? exploring the visual shortcomings of multimodal llms.

Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination Eyes wide shut? exploring the visual shortcomings of multimodal llms

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T10:47:44.634588Z

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 649df8aa-6029-4b67-a3ca-17bab84bd5be · outbound

This paper cites MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation.

Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination MLLM can see? Dynamic Correction Decoding for Hallucination Mitigation

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-10T10:47:44.034645Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55a95a22-9657-428c-8997-9ae74d884b58 · outbound

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

Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination AMBER: An LLM-free Multi-dimensional Benchmark for MLLMs Hallucination Evaluation

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-10T10:47:44.038832Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 910c0aa5-a815-46c1-83b3-d77486dd8de7 · outbound

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

Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-10T10:47:44.043045Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fe3929af-e1b9-4de8-a0b4-6ce2f51ee134 · outbound

This paper cites When Language Overrules: Revealing Text Dominance in Multimodal Large Language Models.

Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination When Language Overrules: Revealing Text Dominance in Multimodal Large Language Models

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-10T10:47:44.047025Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d20456f-62e9-461e-998d-1b1f65351d6d · outbound

This paper cites Mitigating hallucinations in large vision- language models via dpo: On-policy data hold the key.

Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination Mitigating hallucinations in large vision- language models via dpo: On-policy data hold the key

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T10:47:44.622766Z

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 685cf51b-407d-4d66-8d5b-e202331a509f · outbound

This paper cites mplug- owl2: Revolutionizing multi-modal large language model with modality collaboration.

Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination mplug- owl2: Revolutionizing multi-modal large language model with modality collaboration

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-10T10:47:44.055257Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4c5925a-c39d-41ea-8266-012b2ff406ff · outbound

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

Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination Clearsight: Vi- sual signal enhancement for object hallucination mitigation in multimodal large language models

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-10T10:47:44.059547Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02458c0e-89e6-48e6-89a6-b0df3c721b8c · outbound

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

Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination Rlhf-v: Towards trustworthy mllms via behavior alignment from fine-grained correctional hu- man feedback

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T10:47:44.593865Z

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 39a2c8f4-0a3a-4fac-9053-2ff1554b32bc · outbound

This paper cites Mitigating object hallucination in large vision-language models via classifier-free guidance.arXiv e-prints, pages arXiv–2402, 2024.

Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination Mitigating object hallucination in large vision-language models via classifier-free guidance.arXiv e-prints, pages arXiv–2402, 2024

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T10:47:44.580796Z

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 b4d8f383-ae8a-4296-ae4a-e8c09fd8a0e8 · outbound

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

Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-10T10:47:44.071502Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01dad650-bf56-4aed-9657-a284790b120b · outbound

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

Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination Analyzing and Mitigating Object Hallucination in Large Vision-Language Models

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-10T10:47:44.075469Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers