Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding | Paper Citation Record

Observation d23f53f2-0e80-4ab2-bd0b-68d94d3b3213 · outbound

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

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:19.770573Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c91fb18-5a55-4cf9-86b7-e4872a1705cf · outbound

This paper cites Wiki-llava: Hierarchical retrieval-augmented generation for multimodal llms.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Wiki-llava: Hierarchical retrieval-augmented generation for multimodal llms

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:19.840114Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c64b351-e33c-4662-9e2d-6d148fe1668c · outbound

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

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:19.977884Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 502f045d-e5bc-40b2-ba6b-1f0a54df2752 · outbound

This paper cites ShareGPT4V: Improving Large Multi-Modal Models with Better Captions.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding ShareGPT4V: Improving Large Multi-Modal Models with Better Captions

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:20.051069Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e95152e-7ebe-4149-ad62-535492fb4039 · outbound

This paper cites VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:20.133939Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1cf79433-6b9b-4b5e-8dc8-34634e0d97ed · outbound

This paper cites Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality.See https://vicuna.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality.See https://vicuna

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:20.179160Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 983bf124-daaa-4ea4-b362-a13ce4860e92 · outbound

This paper cites Fine-grained Image Captioning with CLIP Reward.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Fine-grained Image Captioning with CLIP Reward

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:20.260110Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44ee6383-35e4-46ce-ab0b-6aa13a2dc0b1 · outbound

This paper cites DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:20.327714Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae458081-5b74-4f6d-856e-2bd5c06560cf · outbound

This paper cites Instructblip: Towards general- purpose vision-language models with instruction tuning,.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Instructblip: Towards general- purpose vision-language models with instruction tuning,

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:20.485861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b49f80b0-80eb-447e-824a-037c1d63326c · outbound

This paper cites InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Model.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding InternLM-XComposer2: Mastering Free-form Text-Image Composition and Comprehension in Vision-Language Large Model

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:20.594782Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70cfe156-4315-4595-bc26-fafad5d8358f · outbound

This paper cites LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:20.690012Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e991a05-b7d3-44da-b212-580538a3440b · outbound

This paper cites Multi-modal hallucination control by visual information grounding.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Multi-modal hallucination control by visual information grounding

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:20.794045Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1118e2c1-0302-482a-9737-069fb582d3b6 · outbound

This paper cites Don't Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaboration.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Don't Hallucinate, Abstain: Identifying LLM Knowledge Gaps via Multi-LLM Collaboration

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:20.864651Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1964c61-00e8-48ee-bdb4-a1162f186914 · outbound

This paper cites Instructdiffusion: A gener- alist modeling interface for vision tasks.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Instructdiffusion: A gener- alist modeling interface for vision tasks

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:20.941996Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc27d80e-ebfd-4ed3-ac40-e7b9176a4f47 · outbound

This paper cites Medsumm: A multimodal approach to summarizing code-mixed hindi- english clinical queries.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Medsumm: A multimodal approach to summarizing code-mixed hindi- english clinical queries

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:21.018310Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8807f823-a1e3-4fe3-92f0-1203ed190709 · outbound

This paper cites Exploring the frontier of vision- language models: A survey of current methodologies and future directions.arXiv preprint arXiv:2404.07214, 2024.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Exploring the frontier of vision- language models: A survey of current methodologies and future directions.arXiv preprint arXiv:2404.07214, 2024

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:21.098044Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5e4965a-5719-49c7-85aa-1ac67756c3cc · outbound

This paper cites Sequence Transduction with Recurrent Neural Networks.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Sequence Transduction with Recurrent Neural Networks

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:21.193304Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 091df255-e653-4d95-ba33-fecbf9168d53 · outbound

This paper cites Detecting and preventing hallucinations in large vision language models.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Detecting and preventing hallucinations in large vision language models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:21.259722Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f645a362-3d5a-4294-a128-edfbeba927de · outbound

This paper cites Vizwiz grand challenge: Answering visual questions from blind people.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Vizwiz grand challenge: Answering visual questions from blind people

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:21.350412Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f899b9f7-38a3-4561-98ed-0208489d5045 · outbound

This paper cites CIEM: Contrastive Instruction Evaluation Method for Better Instruction Tuning.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding CIEM: Contrastive Instruction Evaluation Method for Better Instruction Tuning

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:21.475936Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6857b284-e072-4d24-a64b-cf1d035559df · outbound

This paper cites A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:21.575918Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99577d32-66ba-40f5-86e3-de65a391090b · outbound

This paper cites Diversity-aware meta visual prompting.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Diversity-aware meta visual prompting

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:21.653882Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea8bab2f-73a1-45ac-bf5e-406fbffc1096 · outbound

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

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Opera: Alleviating hallucination in multi- modal large language models via over-trust penalty and retrospection-allocation

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:21.751897Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8ea5553-99ea-443d-ae33-2e4dd930f72c · outbound

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

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Self-Introspective Decoding: Alleviating Hallucinations for Large Vision-Language Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:21.827608Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ce8bb45-f946-4b84-a6d7-1c01dcc9c905 · outbound

This paper cites Vcoder: Ver- satile vision encoders for multimodal large language mod- els.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Vcoder: Ver- satile vision encoders for multimodal large language mod- els

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:21.907491Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb65b76b-9302-47ea-b66e-6e192aa6bae0 · outbound

This paper cites Survey of hallucination in natural language generation.ACM Computing Surveys, 55(12):1–38, 2023.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Survey of hallucination in natural language generation.ACM Computing Surveys, 55(12):1–38, 2023

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:21.973438Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 459f0994-7577-44e8-9f03-8f231c8de0b1 · outbound

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

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Hallucination augmented contrastive learn- ing for multimodal large language model

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:22.049563Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e4f4d98-3a78-4754-95d2-f1379565bfe5 · outbound

This paper cites Chat-univi: Unified visual representation em- powers large language models with image and video under- standing.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Chat-univi: Unified visual representation em- powers large language models with image and video under- standing

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:22.195396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation edcc98b6-1aa8-4d46-9331-e76619db3d84 · outbound

This paper cites Prov- able memorization capacity of msrvtt-qa.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Prov- able memorization capacity of msrvtt-qa

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:22.322023Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6bc61b96-ef38-47c8-8c5d-711e11746c17 · outbound

This paper cites Instructive decoding: Instruction-tuned large lan- guage models are self-refiner from noisy instructions.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Instructive decoding: Instruction-tuned large lan- guage models are self-refiner from noisy instructions

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:22.434952Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 29fda0f7-0ec1-4eee-b4c5-202b66bb1b87 · outbound

This paper cites Lisa: Reasoning segmentation via large language model.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Lisa: Reasoning segmentation via large language model

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:22.501290Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c24cfef3-4c70-4e2f-9ccc-28d47f804e43 · outbound

This paper cites Factuality enhanced lan- guage models for open-ended text generation.NeurIPS, 35: 34586–34599, 2022.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Factuality enhanced lan- guage models for open-ended text generation.NeurIPS, 35: 34586–34599, 2022

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:22.558038Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 584f7466-29e5-47ca-bafc-2e52bc410949 · outbound

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

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Mitigating object hallucinations in large vision-language models through vi- sual contrastive decoding

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:03:38.422622Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 1bab3bb1-5499-490c-abfd-3f732d124096 · outbound

This paper cites LLaVA-OneVision: Easy Visual Task Transfer.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding LLaVA-OneVision: Easy Visual Task Transfer

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:22.686403Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4dd23eff-3d80-42fb-b484-bd080dd491dc · outbound

This paper cites Contrastive Decoding: Open-ended Text Generation as Optimization.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Contrastive Decoding: Open-ended Text Generation as Optimization

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:22.810607Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f46f14f-64b2-47d4-b692-a2bd6f36a557 · outbound

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

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Evaluating object hallucination in large vision-language models

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:03:38.125432Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 26e76795-80b3-4000-81f2-799214232bb2 · outbound

This paper cites Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:23.007971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0b021a32-49be-4a77-9454-b8c85f30648d · outbound

This paper cites Mon- key: Image resolution and text label are important things for large multi-modal models.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Mon- key: Image resolution and text label are important things for large multi-modal models

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:03:37.916331Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation df7bc4f3-da74-46a8-8e91-a393b5344398 · outbound

This paper cites Video-LLaVA: Learning United Visual Representation by Alignment Before Projection.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Video-LLaVA: Learning United Visual Representation by Alignment Before Projection

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:23.331553Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a30dd39-42ae-4820-8f24-2c290d9b0145 · outbound

This paper cites Vila: On pre-training for visual language models, 2023.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Vila: On pre-training for visual language models, 2023

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:03:37.590402Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ce375032-e415-4a2e-ae28-486958255b05 · outbound

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

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:23.464262Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11d7b8dc-834d-4492-baac-39173ea4a923 · outbound

This paper cites Mitigating hallucination in large multi-modal models via robust instruction tuning.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Mitigating hallucination in large multi-modal models via robust instruction tuning

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:03:37.317149Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 39adf377-9bec-4b07-bebe-a7aa3208ec6f · outbound

This paper cites Improved baselines with visual instruction tuning.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Improved baselines with visual instruction tuning

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:03:37.148407Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3aecf81d-45cd-4a79-af05-380f7881ba8b · outbound

This paper cites Visual instruction tuning.Advances in neural infor- mation processing systems, 36, 2024.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Visual instruction tuning.Advances in neural infor- mation processing systems, 36, 2024

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:03:36.924196Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 26d80c7e-5090-4850-a1f7-ee2b8effc5ed · outbound

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

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding A Survey on Hallucination in Large Vision-Language Models

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:23.885022Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ae07e378-1f65-4e3f-8905-ad4b387f0dc7 · outbound

This paper cites PhD: A ChatGPT-Prompted Visual hallucination Evaluation Dataset.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding PhD: A ChatGPT-Prompted Visual hallucination Evaluation Dataset

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:23.949942Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a64e5c6d-92b6-4a91-9844-51687fcfa068 · outbound

This paper cites Paying More Attention to Image: A Training-Free Method for Alleviating Hallucination in LVLMs.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Paying More Attention to Image: A Training-Free Method for Alleviating Hallucination in LVLMs

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:24.001242Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17d08fd7-77a5-4d67-b417-3bfdbf71630e · outbound

This paper cites Unveiling the Ignorance of MLLMs: Seeing Clearly, Answering Incorrectly.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Unveiling the Ignorance of MLLMs: Seeing Clearly, Answering Incorrectly

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:24.060688Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3eba227-0a78-4f3a-8837-3ebc2dfa044d · outbound

This paper cites Mmbench: Is your multi- modal model an all-around player? InEuropean Confer- ence on Computer Vision, pages 216–233.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Mmbench: Is your multi- modal model an all-around player? InEuropean Confer- ence on Computer Vision, pages 216–233

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:03:36.696455Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 06b4c774-7fe0-4669-8bc2-7c5626e8224a · outbound

This paper cites Learn to explain: Multimodal rea- soning via thought chains for science question answering.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Learn to explain: Multimodal rea- soning via thought chains for science question answering

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:03:36.410284Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 34d2350f-0668-4132-aa6d-13956105bb84 · outbound

This paper cites Vista-llama: Reducing hallucination in video language models via equal distance to visual to- kens.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Vista-llama: Reducing hallucination in video language models via equal distance to visual to- kens

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:03:36.100183Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 67807105-ed7a-43e6-a80f-c9407ea955eb · outbound

This paper cites Vista-llama: Reducing hallucination in video language models via equal distance to visual tokens.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Vista-llama: Reducing hallucination in video language models via equal distance to visual tokens

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:03:35.904953Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 10314987-0fbc-4643-941d-b402fbee6f40 · outbound

This paper cites Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:24.639849Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d3fd347-0b41-4e1c-a90f-840739af0721 · outbound

This paper cites Video-chatgpt: Towards detailed video understanding via large vision and language models.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Video-chatgpt: Towards detailed video understanding via large vision and language models

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:03:35.532054Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 73d3b7b6-cbcd-4a5c-b057-8e7f68825568 · outbound

This paper cites SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:24.943812Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3d02633-9be4-4692-80de-134a95a7d6fe · outbound

This paper cites MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:25.101268Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e3628c9-c5ac-4dfd-aa92-9ad1acfa360e · outbound

This paper cites Training lan- guage models to follow instructions with human feedback.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Training lan- guage models to follow instructions with human feedback

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:03:35.201173Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 55db4ed6-38fd-48d6-8dc8-8dae21a3f442 · outbound

This paper cites Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:25.491533Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00432ec0-ea6d-4a31-8b0c-e5a9edde1cf4 · outbound

This paper cites Exploring the limits of transfer learning with a unified text-to-text transformer.The Journal of Ma- chine Learning Research, 21(1):5485–5551, 2020.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Exploring the limits of transfer learning with a unified text-to-text transformer.The Journal of Ma- chine Learning Research, 21(1):5485–5551, 2020

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:03:34.900150Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 9cb3c8b3-090f-4059-86dc-e81f95d2d6ae · outbound

This paper cites Object hallucination in image captioning.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Object hallucination in image captioning

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:03:34.668279Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation dc093ae9-3d08-4a7b-ba04-822102d26e71 · outbound

This paper cites Enhancing Adverse Drug Event Detection with Multimodal Dataset: Corpus Creation and Model Development.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Enhancing Adverse Drug Event Detection with Multimodal Dataset: Corpus Creation and Model Development

Reference 62

Resolution: verified exact; local_arxiv, observed 2026-08-07T15:03:31.181173Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 13883887-e87a-4beb-b2e6-8d9f3efe0886 · outbound

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

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Mitigating Object Hallucination in MLLMs via Data-augmented Phrase-level Alignment

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:26.186307Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f11259f3-fbff-4be3-9342-cff884aae682 · outbound

This paper cites Retrieval Augmentation Reduces Hallucination in Conversation.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Retrieval Augmentation Reduces Hallucination in Conversation

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:26.272534Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4dd9749-d071-4ba1-87ce-4314f8c8b285 · outbound

This paper cites RoFormer: Enhanced Transformer with Rotary Position Embedding.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding RoFormer: Enhanced Transformer with Rotary Position Embedding

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:26.469891Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 843cc290-ba73-41ae-9db9-c482a8ef1168 · outbound

This paper cites Intervening anchor token: Decod- ing strategy in alleviating hallucinations for MLLMs.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Intervening anchor token: Decod- ing strategy in alleviating hallucinations for MLLMs

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:03:34.482930Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b5c93d38-158e-4801-ace1-7429328f6422 · outbound

This paper cites Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:26.756185Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ffb8b9a-bac6-420a-a6dd-812cd0dac30a · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:27.080877Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d41c769a-2ef3-4d64-ac5f-57a8dfb72dcc · outbound

This paper cites Attention is all you need.NeurIPS, 30, 2017.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Attention is all you need.NeurIPS, 30, 2017

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:03:34.119962Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 1243257a-a519-46b3-ae4d-09e4b866d59b · outbound

This paper cites Evaluation and Analysis of Hallucination in Large Vision-Language Models.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Evaluation and Analysis of Hallucination in Large Vision-Language Models

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:27.327901Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0340ce12-f89f-4adc-ad16-dc902035e0d6 · outbound

This paper cites Mitigating Hallucinations in Large Vision-Language Models with Instruction Contrastive Decoding.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Mitigating Hallucinations in Large Vision-Language Models with Instruction Contrastive Decoding

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:27.505799Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a411a925-6063-4579-bdda-4f4889885973 · outbound

This paper cites Self-Instruct: Aligning Language Models with Self-Generated Instructions.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Self-Instruct: Aligning Language Models with Self-Generated Instructions

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:27.605445Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 781dcc68-97e9-48c0-a037-4d2e467f9977 · outbound

This paper cites Logical Closed Loop: Uncovering Object Hallucinations in Large Vision-Language Models.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Logical Closed Loop: Uncovering Object Hallucinations in Large Vision-Language Models

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:27.741065Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b83196bf-c051-4d16-b3fa-47a4e986b32d · outbound

This paper cites Detecting and Mitigating Hallucination in Large Vision Language Models via Fine-Grained AI Feedback.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Detecting and Mitigating Hallucination in Large Vision Language Models via Fine-Grained AI Feedback

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:27.832973Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c8f3bd6-a425-4342-8a02-1807d5796af7 · outbound

This paper cites Mitigating Object Hallucination via Concentric Causal Attention.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Mitigating Object Hallucination via Concentric Causal Attention

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:27.933933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15126a64-f264-45b9-a0c9-c533b5415f3a · outbound

This paper cites Xu, Zhou Zhao, Jun Xiao, Fei Wu, Hanwang Zhang, Xi- angnan He, and Yueting Zhuang.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Xu, Zhou Zhao, Jun Xiao, Fei Wu, Hanwang Zhang, Xi- angnan He, and Yueting Zhuang

Reference 77

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:03:33.737938Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 188b50dc-fb5d-4f7f-bf0f-4b1e1fea118c · outbound

This paper cites MMRC: A Large-Scale Benchmark for Understanding Multimodal Large Language Model in Real-World Conversation.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding MMRC: A Large-Scale Benchmark for Understanding Multimodal Large Language Model in Real-World Conversation

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:28.157713Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59934a67-2ed4-436b-aff0-a48ce80132ec · outbound

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

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding mplug-owl2: Revolutionizing multi-modal large language model with modality collaboration

Reference 79

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:03:33.442051Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 2f3fbd5e-e1e4-4441-85fe-c254df22750a · outbound

This paper cites StableMask: Refining Causal Masking in Decoder-only Transformer.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding StableMask: Refining Causal Masking in Decoder-only Transformer

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:28.377330Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d73112b-e7f0-4497-8605-bec141936938 · outbound

This paper cites Woodpecker: Hallucination Correction for Multimodal Large Language Models.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Woodpecker: Hallucination Correction for Multimodal Large Language Models

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:28.460838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d574b11f-6bbe-47bd-af81-2752e686777e · outbound

This paper cites Ferret: Refer and Ground Anything Anywhere at Any Granularity.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Ferret: Refer and Ground Anything Anywhere at Any Granularity

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:28.536521Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc932b4e-ef19-41d7-a7cf-34d3a41dc2b5 · outbound

This paper cites Yi: Open Foundation Models by 01.AI.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Yi: Open Foundation Models by 01.AI

Reference 83

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:28.637634Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 86c1f11b-8ab2-4d2f-9490-21f17476f577 · outbound

This paper cites Hallucidoctor: Mitigating hallucinatory toxicity in visual instruction data.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Hallucidoctor: Mitigating hallucinatory toxicity in visual instruction data

Reference 84

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:03:33.218471Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b13ca783-03b5-47d8-8cd3-f51f163119d3 · outbound

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

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Rlhf-v: Towards trustworthy mllms via behavior alignment from fine-grained correctional human feedback

Reference 85

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:03:32.917075Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 97ed6509-8848-445c-ac1e-cdff243fbc9c · outbound

This paper cites MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities

Reference 86

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:28.908625Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 013a8dc0-3007-41b1-beed-7273a0e9525b · outbound

This paper cites Less is More: Mitigating Multimodal Hallucination from an EOS Decision Perspective.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Less is More: Mitigating Multimodal Hallucination from an EOS Decision Perspective

Reference 87

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:29.018110Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b91ed071-0510-4fa5-adf3-fe01f5281c13 · outbound

This paper cites HallE-Control: Controlling Object Hallucination in Large Multimodal Models.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding HallE-Control: Controlling Object Hallucination in Large Multimodal Models

Reference 88

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:29.096547Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5000d8aa-ff25-4c8a-91a3-a9a6b1b2bd32 · outbound

This paper cites MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuning.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuning

Reference 89

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:29.190466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c51b01a3-2ccd-4ff9-a9bf-55fd045e6954 · outbound

This paper cites How Language Model Hallucinations Can Snowball.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding How Language Model Hallucinations Can Snowball

Reference 90

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:29.300106Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12f0224a-b699-4faf-899f-9e6326fc8b47 · outbound

This paper cites InternLM-XComposer: A Vision-Language Large Model for Advanced Text-image Comprehension and Composition.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding InternLM-XComposer: A Vision-Language Large Model for Advanced Text-image Comprehension and Composition

Reference 91

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:29.398340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 626231af-986c-44dc-ac73-2ffb654dc266 · outbound

This paper cites InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output

Reference 92

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:29.481580Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7234766-8a0d-436a-8830-fa2b8793f0d3 · outbound

This paper cites Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models

Reference 93

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:29.578054Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b30317a4-5144-4870-8953-6eb0fed9b8cf · outbound

This paper cites Recognize anything: A strong image tagging model.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Recognize anything: A strong image tagging model

Reference 94

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T15:03:32.537395Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 40201650-cfc0-40bf-a017-9135530d8ab7 · outbound

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

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization

Reference 95

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:29.814792Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d5bf860-658c-4767-b3e8-e50cce7029db · outbound

This paper cites Investigating and Mitigating the Multimodal Hallucination Snowballing in Large Vision-Language Models.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Investigating and Mitigating the Multimodal Hallucination Snowballing in Large Vision-Language Models

Reference 96

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:29.916827Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fafaa6f1-3eab-4da1-aafc-f779f3ab0f22 · outbound

This paper cites an unresolved cited work.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Unresolved cited work

Reference 97

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:03:32.130731Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5864be9c-31cb-4bbe-836d-8baf52b454b7 · outbound

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

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding Analyzing and Mitigating Object Hallucination in Large Vision-Language Models

Reference 98

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:30.087943Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25fa4015-cf3d-4412-aa06-b645ba09fe3b · outbound

This paper cites MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models

Reference 99

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:30.195388Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60b004da-e17e-4fea-9fcb-4baadb6f541c · outbound

This paper cites IBD: Alleviating Hallucinations in Large Vision-Language Models via Image-Biased Decoding.

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding IBD: Alleviating Hallucinations in Large Vision-Language Models via Image-Biased Decoding

Reference 100

Resolution: unresolved; no resolver link, observed 2026-08-07T15:03:30.301678Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers