Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-05-12T05:15:34.156717Z
Paper Citation Record · LEDGER
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination
As of 6 August 2026, this Paper Citation Record lists 100 of 120 outbound references and 1 inbound Pith citation observation for arXiv:2605.10622.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-05T06:32:48.257954+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-05-20T15:16:24.651868Z
A source-named dated measurement, never combined with another source.
Source: pith, observed 2026-05-20T15:18:25.443496Z
Reference resolution
100 of 120 outbound references displayed
- verified exact8
- verified fuzzy56
- unresolved14
- parse uncertain0
- malformed identifier0
- metadata mismatch22
External citation measurements
No source-named external measurement is stored.
Outbound references
Observation d3cd2a54-3934-42e4-aae8-e2cc1aaa9768 · outbound
This paper cites Aligning Large Multimodal Models with Factually Augmented.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Aligning Large Multimodal Models with Factually Augmented
Reference 1
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T11:46:33.803774Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 5405ca89-cdc7-4250-9593-2fe3bd51d9cb · outbound
This paper cites Proceedings of the International Conference on Learning Representations (ICLR) , year=.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Proceedings of the International Conference on Learning Representations (ICLR) , year=
Reference 2
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T11:46:33.811067Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 308cf280-2469-4579-808e-915e108c0a7d · outbound
This paper cites Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , pages =.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , pages =
Reference 3
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T11:46:33.814678Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 776a4081-c7a1-4a66-b08f-2b301bb6502b · outbound
This paper cites Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , pages =.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , pages =
Reference 4
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T11:46:33.796781Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 9f864e6a-5444-4f97-bde1-09d79b9fbb37 · outbound
This paper cites Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , pages =.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , pages =
Reference 5
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T11:46:33.800528Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation d79ca27b-c24b-4bcc-b23c-c200c5be4dd3 · outbound
This paper cites Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , pages=.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , pages=
Reference 7
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T11:46:33.807275Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation ffbdc1ec-ecb5-437c-adf6-63ef1d32d0f6 · outbound
This paper cites Understanding Alignment in Multimodal LLMs: A Comprehensive Study.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Understanding Alignment in Multimodal LLMs: A Comprehensive Study
Reference 10
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T05:16:24.424276Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation c3b1941b-01a1-4df4-a2e1-b25a5a270fb8 · outbound
This paper cites Proceedings of the Advances in neural information processing systems (NeurIPS) , year=.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Proceedings of the Advances in neural information processing systems (NeurIPS) , year=
Reference 11
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T11:46:33.485492Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 8f01fa6f-2dfb-48b3-b38a-f715135ba2da · outbound
This paper cites A topic-level self-correctional ap- proach to mitigate hallucinations in mllms.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination A topic-level self-correctional ap- proach to mitigate hallucinations in mllms
Reference 12
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T05:16:24.399892Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation f8cfc95c-250d-42f4-bc1f-f69193195ebc · outbound
This paper cites Proceedings of the European Conference on Computer Vision (ECCV) , pages=.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Proceedings of the European Conference on Computer Vision (ECCV) , pages=
Reference 13
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T11:46:33.785940Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 8dde4a42-f19c-4c12-b820-a25c8438dede · outbound
This paper cites 2023 , archivePrefix=.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination 2023 , archivePrefix=
Reference 14
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T11:46:33.609857Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 40d38145-8f16-4a24-9be5-f7d8969a19f7 · outbound
This paper cites Detecting and Mitigating Hallucination in Large Vision Language Models via Fine-Grained AI Feedback.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Detecting and Mitigating Hallucination in Large Vision Language Models via Fine-Grained AI Feedback
Reference 15
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T05:16:24.385179Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 01786860-bea6-44e9-a90a-94a0bac685c6 · outbound
This paper cites Proceedings of the International Conference on Learning Representations (ICLR) , year=.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Proceedings of the International Conference on Learning Representations (ICLR) , year=
Reference 16
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T11:46:33.613747Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 86225494-a19a-49a6-8132-209bb3a59448 · outbound
This paper cites Modality-Fair Preference Optimization for Trustworthy MLLM Alignment.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Modality-Fair Preference Optimization for Trustworthy MLLM Alignment
Reference 17
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T05:16:24.380561Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation f4ab89db-1aee-4fdc-875a-85766e9a3ce1 · outbound
This paper cites Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP) , pages=.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP) , pages=
Reference 18
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T11:46:33.789784Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation dea9e855-50d1-4f9c-898d-6b40f6ee56bc · outbound
This paper cites SimPO: Simple Preference Optimization with a Reference-Free Reward.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination SimPO: Simple Preference Optimization with a Reference-Free Reward
Reference 19
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T05:16:24.389232Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation a3ab9b5e-2649-429d-bcb5-248393799ab6 · outbound
This paper cites Noise Contrastive Alignment of Language Models with Explicit Rewards.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Noise Contrastive Alignment of Language Models with Explicit Rewards
Reference 20
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T05:16:24.403876Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation eeb00b8b-20d5-45bc-b1ec-ae68f32677e4 · outbound
This paper cites Proceedings of the Advances in Neural Information Processing Systems (NeurIPS) , year=.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Proceedings of the Advances in Neural Information Processing Systems (NeurIPS) , year=
Reference 21
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T11:46:33.620854Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation b73af5eb-ba18-4abb-811d-2a2329e965ae · outbound
This paper cites A Comprehensive Overview of Large Language Models.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination A Comprehensive Overview of Large Language Models
Reference 22
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-19T20:28:39.632097Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 8c80b0a8-832b-403f-a782-a998c1161e72 · outbound
This paper cites Challenges and Applications of Large Language Models.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Challenges and Applications of Large Language Models
Reference 23
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T05:16:24.353175Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation af2d479b-7a12-4cf3-99eb-dfa6cd63f7e0 · outbound
This paper cites A Survey of Large Language Models.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination A Survey of Large Language Models
Reference 24
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-12T05:16:24.349251Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 883636bf-cbfa-40da-8a7d-62ff0b112b82 · outbound
This paper cites Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment
Reference 25
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T05:16:24.376482Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 82e7b991-bf12-4df8-8813-6e3228f29d71 · outbound
This paper cites The method of paired comparisons , author=.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination The method of paired comparisons , author=
Reference 26
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T11:46:33.481768Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation cb160832-fda9-4168-94ba-41e881d76b79 · outbound
This paper cites Proceedings of the Advances in Neural Information Processing Systems (NeurIPS) , year=.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Proceedings of the Advances in Neural Information Processing Systems (NeurIPS) , year=
Reference 27
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T11:46:33.793473Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation a8992638-c2ef-4dbb-82ad-7147baf82ac0 · outbound
This paper cites Proceedings of the Advances in Neural Information Processing Systems (NeurIPS) , year=.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Proceedings of the Advances in Neural Information Processing Systems (NeurIPS) , year=
Reference 28
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T11:46:33.588184Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 472b4537-f73b-4768-90be-0b63f2d3106e · outbound
This paper cites Transactions on Machine Learning Research (TMLR) , volume =.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Transactions on Machine Learning Research (TMLR) , volume =
Reference 29
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T11:46:33.606423Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 773c1a20-89f8-4acd-850b-7823a954b94f · outbound
This paper cites Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , pages=.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , pages=
Reference 30
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T11:46:33.637227Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 9022b574-d221-43b9-8030-d0f333eba845 · outbound
This paper cites https://vicuna.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination https://vicuna
Reference 31
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T11:46:33.577347Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 74821e2e-5781-45f6-b408-f41a4ed99e11 · outbound
This paper cites Proceedings of the International Conference on Machine Learning (ICML) , pages=.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Proceedings of the International Conference on Machine Learning (ICML) , pages=
Reference 32
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T11:46:33.584669Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 28772c41-9eae-4580-856b-a0874090390b · outbound
This paper cites CHiP: Cross-modal Hierarchical Direct Preference Optimization for Multimodal LLMs.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination CHiP: Cross-modal Hierarchical Direct Preference Optimization for Multimodal LLMs
Reference 33
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T05:16:24.341461Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 2e17c096-6cb2-40dc-9191-4e9e52c596d3 · outbound
This paper cites Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP) , pages=.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP) , pages=
Reference 34
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T11:46:33.676548Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 5c6f3828-4524-4c43-bf00-401a30b44cb6 · outbound
This paper cites GPT-4 Technical Report.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination GPT-4 Technical Report
Reference 35
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-12T05:16:24.345148Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 76beaf9e-7ac6-4db0-9504-6e5a17747400 · outbound
This paper cites Proceedings of the Advances in Neural Information Processing Systems (NeurIPS) , year =.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Proceedings of the Advances in Neural Information Processing Systems (NeurIPS) , year =
Reference 37
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T11:46:33.501063Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 8044d51e-823e-42da-955c-dfcf3f95e7e8 · outbound
This paper cites an unresolved cited work.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Unresolved cited work
Reference 38
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T11:46:33.764927Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation d94c4dde-b515-4c95-995f-21528a28fbf4 · outbound
This paper cites Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond
Reference 39
- Resolution
- metadata mismatch
- local_arxiv, observed 2026-05-12T05:16:24.418342Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 383a6ae6-9379-4b82-9073-4a7e65d3b7b9 · outbound
This paper cites Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimization
Reference 40
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-17T10:52:37.519567Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation c9a9a304-51f9-46f2-bc08-1a4dcf516221 · outbound
This paper cites Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP) , pages =.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP) , pages =
Reference 41
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T11:46:33.570753Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation eb5ea195-2b37-4f18-bba0-eb99570b148b · outbound
This paper cites Proceedings of the Advances in Neural Information Processing Systems (NeurIPS) , year=.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Proceedings of the Advances in Neural Information Processing Systems (NeurIPS) , year=
Reference 43
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T11:46:33.742708Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 58357913-4f46-407a-b8e3-41b510217464 · outbound
This paper cites Proceedings of the European Conference on Computer Vision (ECCV) , pages=.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Proceedings of the European Conference on Computer Vision (ECCV) , pages=
Reference 44
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T11:46:33.541950Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 5e3bc017-df10-4b9c-b633-e5c50d2e172d · outbound
This paper cites Proceedings of the International Conference on Machine Learning (ICML) , year =.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Proceedings of the International Conference on Machine Learning (ICML) , year =
Reference 45
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T11:46:33.641152Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 11827e9e-a443-4ebd-8c5e-9281ddc6cf15 · outbound
This paper cites A Survey on Hallucination in Large Vision-Language Models.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination A Survey on Hallucination in Large Vision-Language Models
Reference 46
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-13T22:10:10.379182Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 7413d8bf-e675-4e38-8342-9d9d3c93c0c3 · outbound
This paper cites Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP) , pages=.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP) , pages=
Reference 47
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T11:46:33.664885Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 5e3e9c1d-3695-4728-a0f0-e488bfbba7b3 · outbound
This paper cites Proceedings of the International Conference on Learning Representations (ICLR) , year=.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Proceedings of the International Conference on Learning Representations (ICLR) , year=
Reference 48
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T11:46:33.534621Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation e0825748-a7a5-4245-82f9-c075ad3c820f · outbound
This paper cites HallE-Control: Controlling Object Hallucination in Large Multimodal Models.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination HallE-Control: Controlling Object Hallucination in Large Multimodal Models
Reference 49
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T05:16:24.217827Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 0515d51c-440a-42c4-9d4d-646fd5a981a3 · outbound
This paper cites Mitigating Object Hallucination in Large Vision-Language Models via Image-Grounded Guidance.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Mitigating Object Hallucination in Large Vision-Language Models via Image-Grounded Guidance
Reference 50
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T05:16:24.225433Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 922a419b-588b-42ce-b547-b5f046701bd5 · outbound
This paper cites Proceedings of the AAAI Conference on Artificial Intelligence (AAAI) , volume=.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Proceedings of the AAAI Conference on Artificial Intelligence (AAAI) , volume=
Reference 51
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T11:46:33.538419Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 55069ce5-55ba-4b8c-b471-930e564833dd · outbound
This paper cites Woodpecker: Hallucination Correction for Multimodal Large Language Models.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Woodpecker: Hallucination Correction for Multimodal Large Language Models
Reference 52
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T05:16:24.277730Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 2fc9b06f-d72d-4c31-8fa6-d75f0e660f72 · outbound
This paper cites Proceedings of the International Conference on Machine Learning (ICML) , year=.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Proceedings of the International Conference on Machine Learning (ICML) , year=
Reference 53
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T11:46:33.559894Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation b2c012a2-6c3b-4121-a850-c3a349406986 · outbound
This paper cites Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal Large Language Models.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal Large Language Models
Reference 54
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T05:16:24.288612Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 8b580fb3-13b9-411d-9479-7162fc8a75c4 · outbound
This paper cites arXiv e-prints , pages=.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination arXiv e-prints , pages=
Reference 55
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T11:46:33.645087Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation e18c5ca0-6a5c-47b6-8d7c-471253496369 · outbound
This paper cites Proceedings of the International Conference on Learning Representations (ICLR) , year=.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Proceedings of the International Conference on Learning Representations (ICLR) , year=
Reference 56
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T11:46:33.657159Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 39eac54b-5d14-4dc8-b336-f53008c64bfc · outbound
This paper cites Aligning Large Multimodal Models with Factually Augmented.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Aligning Large Multimodal Models with Factually Augmented
Reference 57
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T11:46:33.668752Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation eb15ce03-13b6-46af-9b05-b7d08b7704e2 · outbound
This paper cites Aligning Modalities in Vision Large Language Models via Preference Fine-tuning.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Aligning Modalities in Vision Large Language Models via Preference Fine-tuning
Reference 58
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-17T10:58:53.893696Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation beb0ae28-ab6c-4f56-bd2e-8b537cbe3c61 · outbound
This paper cites Proceedings of the Advances in Neural Information Processing Systems (NeurIPS) , year =.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Proceedings of the Advances in Neural Information Processing Systems (NeurIPS) , year =
Reference 59
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T11:46:33.545612Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation f2fc7056-c601-4128-a7a6-8224f7f656a3 · outbound
This paper cites Proceedings of the International Conference on Learning Representations (ICLR) , year=.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Proceedings of the International Conference on Learning Representations (ICLR) , year=
Reference 60
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T11:46:33.751825Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation ee5a3004-cd53-44cb-a7b9-fb874b80432e · outbound
This paper cites Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP) , pages=.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP) , pages=
Reference 61
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T11:46:33.653093Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 7d759a14-f5dc-4610-b9e9-d44b0e5b599e · outbound
This paper cites Proceedings of the Advances in Neural Information Processing Systems (NeurIPS) , year =.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Proceedings of the Advances in Neural Information Processing Systems (NeurIPS) , year =
Reference 62
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T11:46:33.758651Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 91137680-0747-4215-a620-0cf995995958 · outbound
This paper cites Proceedings of the IEEE conference on computer vision and pattern recognition , pages=.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Proceedings of the IEEE conference on computer vision and pattern recognition , pages=
Reference 63
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T11:46:33.649112Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 7d33e974-849a-4a29-b476-9824ac215692 · outbound
This paper cites CVPR , year=.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination CVPR , year=
Reference 64
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T11:46:33.679835Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 74adde11-3931-4a25-a8ad-81c95faa1503 · outbound
This paper cites Proceedings of the IEEE conference on computer vision and pattern recognition , pages=.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Proceedings of the IEEE conference on computer vision and pattern recognition , pages=
Reference 65
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T11:46:33.729093Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 34c34a2d-6127-4e99-a2ac-2556ab246414 · outbound
This paper cites InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning
Reference 66
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-13T02:13:52.361122Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation edf27380-7caa-42c6-b39e-6681b1ef0186 · outbound
This paper cites Advances in Neural Information Processing Systems (NeurIPS) , year=.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Advances in Neural Information Processing Systems (NeurIPS) , year=
Reference 67
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T11:46:33.526880Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 11436be9-3937-49bc-b078-4b469d4da9d7 · outbound
This paper cites Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=
Reference 68
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T11:46:33.530862Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 730f986a-79d8-4e74-8bc3-8b30422f692f · outbound
This paper cites MMBench: Is Your Multi-modal Model an All-around Player?.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination MMBench: Is Your Multi-modal Model an All-around Player?
Reference 70
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T17:20:54.147488Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 948b2143-8782-46d8-a398-855fe7cec457 · outbound
This paper cites Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive
Reference 71
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-17T23:04:44.937279Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation a03825eb-bee6-49c0-bfec-9aff0bbd99d1 · outbound
This paper cites Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , pages=.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , pages=
Reference 72
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T11:46:33.633010Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation b03a725b-d0d4-44f8-8d65-55c721f049d5 · outbound
This paper cites The Thirteenth International Conference on Learning Representations.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination The Thirteenth International Conference on Learning Representations
Reference 73
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T11:46:33.493792Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation ea74b8f5-9e0e-4191-8a50-34700be059a3 · outbound
This paper cites Massive Activations in Large Language Models.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Massive Activations in Large Language Models
Reference 74
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-16T07:02:54.298502Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation eae42526-8f2a-4b02-813f-b5f8481334bb · outbound
This paper cites The Thirteenth International Conference on Learning Representations (ICLR) , year=.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination The Thirteenth International Conference on Learning Representations (ICLR) , year=
Reference 75
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T11:46:33.598896Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 829ea2c8-a18f-452c-b946-8e5c2079c055 · outbound
This paper cites Forty-second International Conference on Machine Learning (ICLR) , year=.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Forty-second International Conference on Machine Learning (ICLR) , year=
Reference 78
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T11:46:33.725381Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation d853f730-d38c-44f4-bad0-fbdc964868c1 · outbound
This paper cites an unresolved cited work.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Unresolved cited work
Reference 79
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T11:46:33.745560Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 757af40b-7d50-484a-a650-b861a9f5f761 · outbound
This paper cites LLaVA-NeXT: Improved reasoning, OCR, and world knowledge , url=.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination LLaVA-NeXT: Improved reasoning, OCR, and world knowledge , url=
Reference 80
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T11:46:33.761800Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 59b92358-2768-4a2c-a4be-ba53d0d81a16 · outbound
This paper cites Transformer Circuits Thread , volume=.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Transformer Circuits Thread , volume=
Reference 81
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T11:46:33.672892Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 753585a1-fe72-4927-867e-16faccddc5cb · outbound
This paper cites Information Flow Routes: Automatically Interpreting Language Models at Scale.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Information Flow Routes: Automatically Interpreting Language Models at Scale
Reference 83
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T05:16:24.303047Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation cb54c0f4-c3b1-4f05-8a2c-fd1553b34198 · outbound
This paper cites Spectral Filters, Dark Signals, and Attention Sinks.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Spectral Filters, Dark Signals, and Attention Sinks
Reference 84
- Resolution
- metadata mismatch
- arxiv_id, observed 2026-05-12T05:16:24.204146Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation bd8adb01-9b60-4f92-a7ec-26a062527e6f · outbound
This paper cites Computer Vision--ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014 , year=.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Computer Vision--ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014 , year=
Reference 85
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T11:46:33.624577Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 0ac9fdde-b7b0-4beb-a219-6e3f6fb074ee · outbound
This paper cites ATMAN: Understanding Transformer Predictions Through Memory Efficient Attention Manipulation , volume =.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination ATMAN: Understanding Transformer Predictions Through Memory Efficient Attention Manipulation , volume =
Reference 86
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T11:46:33.767948Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation bbc1f9f1-9c29-4c4d-b60a-1530a075c2e8 · outbound
This paper cites Tell Your Model Where to Attend: Post-hoc Attention Steering for.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Tell Your Model Where to Attend: Post-hoc Attention Steering for
Reference 87
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T11:46:33.489522Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 1dbf3a25-6c52-429a-bbbe-cc06100486c9 · outbound
This paper cites Model Tells You What to Discard: Adaptive.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Model Tells You What to Discard: Adaptive
Reference 88
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T11:46:33.617515Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 9d7e0979-082a-4a49-92e3-41de4df60db1 · outbound
This paper cites an unresolved cited work.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Unresolved cited work
Reference 90
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T11:46:33.591537Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 8cf0d81a-18fe-41cb-83d3-f769010380c1 · outbound
This paper cites Adaptive Foundation Models: Evolving AI for Personalized and Efficient Learning , year=.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Adaptive Foundation Models: Evolving AI for Personalized and Efficient Learning , year=
Reference 91
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T11:46:33.595279Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 2857e01e-901f-400f-8aeb-6e093fb1562c · outbound
This paper cites Findings of the Association for Computational Linguistics: ACL 2025 , year=.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Findings of the Association for Computational Linguistics: ACL 2025 , year=
Reference 92
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T11:46:33.505009Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 6125be6c-2cae-41d7-a612-18b56525ec3c · outbound
This paper cites IEEE Transactions on Systems, Man, and Cybernetics , volume=.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination IEEE Transactions on Systems, Man, and Cybernetics , volume=
Reference 93
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T11:46:33.563436Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 16a468ac-244b-4567-892b-4ea948ab8497 · outbound
This paper cites Proceedings of the International Conference on Learning Representations (ICLR) , year=.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Proceedings of the International Conference on Learning Representations (ICLR) , year=
Reference 95
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T11:46:33.553053Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 704d3768-fceb-4477-844c-a88a417b2c65 · outbound
This paper cites The Thirty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS) , year=.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination The Thirty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS) , year=
Reference 97
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-05-12T11:46:33.660939Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 5b943fd6-456a-4c89-aac5-febd2b7cd1d3 · outbound
This paper cites Hallucination of Multimodal Large Language Models: A Survey.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Hallucination of Multimodal Large Language Models: A Survey
Reference 98
- Resolution
- verified exact
- local_arxiv, observed 2026-05-12T05:16:24.356912Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 7958adc2-68b2-48f2-8aed-c6eb27141213 · outbound
This paper cites Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic
Reference 99
- Resolution
- verified exact
- arxiv_id, observed 2026-05-12T15:52:36.167809Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation dec41afd-89cc-4f52-840d-b2bf7bbff141 · outbound
This paper cites an unresolved cited work.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Unresolved cited work
Reference 100
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T11:46:33.721335Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 01f463d1-2316-4d76-b63e-d927a9e12691 · outbound
This paper cites an unresolved cited work.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Unresolved cited work
Reference 101
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T11:46:33.755249Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation b886e7e9-73d3-4e89-a940-a1c8aecaa2c3 · outbound
This paper cites In: Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (2025).
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination In: Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) (2025)
Reference 102
- Resolution
- verified exact
- doi, observed 2026-05-12T05:16:22.197174Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 465ea9d5-eff6-4f0b-b5ad-dfa8949ada57 · outbound
This paper cites an unresolved cited work.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Unresolved cited work
Reference 103
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T11:46:33.782046Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 4d679d92-d6ce-48e3-b709-cb67115417af · outbound
This paper cites an unresolved cited work.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Unresolved cited work
Reference 104
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T11:46:33.556490Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 6e3474e5-b100-420f-a7c7-aa21c07da82a · outbound
This paper cites an unresolved cited work.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Unresolved cited work
Reference 105
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T11:46:33.739292Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 90658a9a-e9d7-4c50-9a2a-213517a2f449 · outbound
This paper cites MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models
Reference 106
- Resolution
- verified exact
- local_arxiv, observed 2026-05-12T05:16:24.196961Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation ad7d50cd-88fe-479a-a360-fb340de3f053 · outbound
This paper cites an unresolved cited work.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Unresolved cited work
Reference 107
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T11:46:33.774733Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation a2a90088-9a33-4892-a930-1a84284c8e52 · outbound
This paper cites an unresolved cited work.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Unresolved cited work
Reference 108
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T11:46:33.778001Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 903c9cc0-7e89-4c67-bc19-75e0bf574b0b · outbound
This paper cites an unresolved cited work.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Unresolved cited work
Reference 109
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T11:46:33.748640Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation ab898d91-4e95-407d-9fe9-2312ac5ee84c · outbound
This paper cites an unresolved cited work.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Unresolved cited work
Reference 110
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T11:46:33.523215Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation d93a8b7a-21fa-4715-8d6a-d70a2ac299db · outbound
This paper cites an unresolved cited work.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Unresolved cited work
Reference 111
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T11:46:33.549162Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Observation 84dab43c-2618-45a9-b32e-976c8b062193 · outbound
This paper cites an unresolved cited work.
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination Unresolved cited work
Reference 112
- Resolution
- unresolved
- raw_fallback, observed 2026-05-12T11:46:33.574063Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.
Pith citing papers
Observation cd07c8b2-76e4-4fb8-87c6-b55116b53523 · inbound
Dynamic Model Merging Made Slim cites this paper.
Dynamic Model Merging Made Slim Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination
Reference 8
- Resolution
- verified exact
- local_arxiv, observed 2026-05-20T15:18:25.445076Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.