Paper Citation Record · LEDGER

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation

As of 19 August 2026, this Paper Citation Record lists 57 of 57 outbound references and 1 inbound Pith citation observation for arXiv:2506.12609.

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

pith.paper-citation-record.v1
2506.12609 v2

Coverage vector

measured 57 of 57 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T00:53:27.104761Z

measured 58 of 58 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-19T06:32:44.657259+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-01T08:35:58.508826Z

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

57 of 57 outbound references displayed

verified exact1
verified fuzzy0
unresolved56
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 976d75ba-83e9-4bb5-93ff-73df9c719db5 · outbound

This paper cites , " * write output.state after.block = add.period write newline.

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation , " * write output.state after.block = add.period write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T00:53:22.575055Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bdffb986-9975-464a-80c5-7a082924b70e · outbound

This paper cites write newline.

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation write newline

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T00:53:22.618859Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation efeb766d-455e-40ad-9d07-e7c2dc5f2b74 · outbound

This paper cites an unresolved cited work.

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation Unresolved cited work

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T00:53:22.665692Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ccd1d10b-e723-4d08-9bcf-5f0e244c7998 · outbound

This paper cites Mitigating Object Hallucinations in Large Vision-Language Models with Assembly of Global and Local Attention.

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation Mitigating Object Hallucinations in Large Vision-Language Models with Assembly of Global and Local Attention

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T00:53:22.725809Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 991ed59a-4b89-40cb-91a4-a37528e7e6f1 · outbound

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

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T00:53:22.759317Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4cc2c136-08c7-4101-a11b-b7bb540aaac0 · outbound

This paper cites Qwen2.5-VL Technical Report.

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation Qwen2.5-VL Technical Report

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T00:53:22.815186Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 025bc15a-1b16-449e-a139-60cba9df9944 · outbound

This paper cites PerturboLLaVA: Reducing Multimodal Hallucinations with Perturbative Visual Training.

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation PerturboLLaVA: Reducing Multimodal Hallucinations with Perturbative Visual Training

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T00:53:22.876621Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16af127f-47f4-48fe-a3ef-9c70f2aad857 · outbound

This paper cites MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning.

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation MiniGPT-v2: large language model as a unified interface for vision-language multi-task learning

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T00:53:22.919362Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec4f0683-7bc1-4261-b437-94e8fe71ec2e · outbound

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

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T00:53:22.987103Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e98a53c0-f2af-4000-b3f4-8dbfb4fff43c · outbound

This paper cites Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling.

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T00:53:23.040170Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 353f834a-a8a2-4597-a58a-2f7870219647 · outbound

This paper cites an unresolved cited work.

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation Unresolved cited work

Reference 11

Resolution: unresolved; raw_fallback, observed 2026-08-07T00:53:29.954781Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 1cc386ed-fdcb-4797-969c-8f80b00c26bf · outbound

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

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T00:53:23.163877Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2ee1f1d-3a28-461a-b97a-43dff37a64be · outbound

This paper cites an unresolved cited work.

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation Unresolved cited work

Reference 13

Resolution: unresolved; raw_fallback, observed 2026-08-07T00:53:29.794102Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 6df37b77-c251-432b-9c7c-90921c7a7f0c · outbound

This paper cites an unresolved cited work.

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation Unresolved cited work

Reference 14

Resolution: unresolved; raw_fallback, observed 2026-08-07T00:53:29.546621Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation a34f09ec-c22c-4e0a-8fc9-8c0af8f096e0 · outbound

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

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T00:53:23.324055Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b2a52a9-b3f1-46a8-b6f7-745c09a152ac · outbound

This paper cites Vision Transformers Need Registers.

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation Vision Transformers Need Registers

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T00:53:23.384541Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3c6ee9c-3069-4d7d-b49f-bdb5242bdee6 · outbound

This paper cites Improving Complex Reasoning with Dynamic Prompt Corruption: A soft prompt Optimization Approach.

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation Improving Complex Reasoning with Dynamic Prompt Corruption: A soft prompt Optimization Approach

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T00:53:23.469925Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation afdb2e5d-de51-4465-818f-16622ba0c007 · outbound

This paper cites an unresolved cited work.

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation Unresolved cited work

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T00:53:23.516171Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c728cfc-5801-4b44-90b4-46367db551c8 · outbound

This paper cites an unresolved cited work.

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation Unresolved cited work

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T00:53:23.654358Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44d606a3-dd9c-4435-898b-08eb301f1487 · outbound

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

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation Self-Introspective Decoding: Alleviating Hallucinations for Large Vision-Language Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T00:53:23.688315Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b914d2a2-ee8d-4541-9176-1295124fdfe4 · outbound

This paper cites an unresolved cited work.

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation Unresolved cited work

Reference 21

Resolution: unresolved; raw_fallback, observed 2026-08-07T00:53:29.309145Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation e6765169-2bf6-441f-932a-d0bc6ad9374f · outbound

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

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation See What You Are Told: Visual Attention Sink in Large Multimodal Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T00:53:23.816759Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a094aa3-40f1-4c28-b322-ab29671908d2 · outbound

This paper cites an unresolved cited work.

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation Unresolved cited work

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T00:53:23.882361Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77bd41b0-188c-4a82-9eb6-535bc497b96b · outbound

This paper cites an unresolved cited work.

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation Unresolved cited work

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T00:53:23.964934Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5335684e-c19c-4d84-970a-50f8763393d1 · outbound

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

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation Evaluating Object Hallucination in Large Vision-Language Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T00:53:24.010453Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1e88564e-c8c0-4246-81a3-84b8cf316904 · outbound

This paper cites an unresolved cited work.

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation Unresolved cited work

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T00:53:24.084140Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0e3b222-8988-4ad4-9719-57eb7c745041 · outbound

This paper cites an unresolved cited work.

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation Unresolved cited work

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T00:53:24.215125Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba6b25c8-6df4-4678-89c9-5c3b60fa3825 · outbound

This paper cites an unresolved cited work.

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation Unresolved cited work

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T00:53:24.287494Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b78fbe27-3ff4-459f-9e91-f39754e31d7f · outbound

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

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation A Survey on Hallucination in Large Vision-Language Models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T00:53:24.325737Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dfcdb7ec-bee2-4410-9c03-f85eb9ce1b85 · outbound

This paper cites Reducing Hallucinations in Vision-Language Models via Latent Space Steering.

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation Reducing Hallucinations in Vision-Language Models via Latent Space Steering

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T00:53:24.416065Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 751489cf-3c15-4379-b4ba-592c2ba368cb · outbound

This paper cites an unresolved cited work.

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation Unresolved cited work

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T00:53:24.503141Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 399d0d16-6160-4f20-8dfa-5df5ccf96557 · outbound

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

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T00:53:24.583608Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 040dc1e2-824a-4182-9459-58b7d607a840 · outbound

This paper cites an unresolved cited work.

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation Unresolved cited work

Reference 33

Resolution: unresolved; raw_fallback, observed 2026-08-07T00:53:29.024955Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 20704f3a-0492-4d9a-9689-922bdc82cb96 · outbound

This paper cites an unresolved cited work.

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation Unresolved cited work

Reference 34

Resolution: unresolved; raw_fallback, observed 2026-08-07T00:53:28.808428Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation f2fca7e3-7018-4aa6-b234-20f19fe9ba46 · outbound

This paper cites Object Hallucination in Image Captioning.

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation Object Hallucination in Image Captioning

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T00:53:24.839134Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d129c012-6cc2-400f-b314-b3ba900413d5 · outbound

This paper cites Do we really have to filter out random noise in pre-training data for language models?.

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation Do we really have to filter out random noise in pre-training data for language models?

Reference 36

Resolution: verified exact; local_arxiv, observed 2026-08-07T00:53:27.615962Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 5e45eba6-e621-422a-b528-4c4606d2adba · outbound

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

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation Mitigating Object Hallucination in MLLMs via Data-augmented Phrase-level Alignment

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T00:53:25.018219Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 274b3317-9066-4f05-8933-1b331096732d · outbound

This paper cites Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps.

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T00:53:25.143930Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92332fac-e4db-4bbe-a526-2c19c7c5f226 · outbound

This paper cites an unresolved cited work.

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation Unresolved cited work

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T00:53:25.331826Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0570a4fb-5546-4735-bff3-373a8c3fe983 · outbound

This paper cites an unresolved cited work.

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation Unresolved cited work

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T00:53:25.465791Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c1b29c9-6521-4e8d-8801-c9095f5537cc · outbound

This paper cites an unresolved cited work.

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation Unresolved cited work

Reference 41

Resolution: unresolved; raw_fallback, observed 2026-08-07T00:53:28.677413Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 09035a42-d416-4833-9de1-477886362946 · outbound

This paper cites Qwen2 Technical Report.

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation Qwen2 Technical Report

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T00:53:25.735588Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa9f3640-605e-4a39-99c3-2d87a789f7c4 · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation LLaMA: Open and Efficient Foundation Language Models

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T00:53:25.831284Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f7ccba4-72b1-41af-b2b7-dd210c793768 · outbound

This paper cites Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning.

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T00:53:25.946504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 54bd6f6a-e4a1-47ad-8ea6-3a529d4e83a7 · outbound

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

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T00:53:26.114873Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c0e1674-a134-4e1e-b300-781af4bf527f · outbound

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

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation Mitigating Hallucinations in Large Vision-Language Models with Instruction Contrastive Decoding

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-07T00:53:26.193559Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56faeddd-8085-42e6-9726-bff8ea74ab95 · outbound

This paper cites an unresolved cited work.

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation Unresolved cited work

Reference 47

Resolution: unresolved; raw_fallback, observed 2026-08-07T00:53:28.557614Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 8369fb3f-6d60-45bf-89cd-5d65b3e686c5 · outbound

This paper cites Qwen3 Technical Report.

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation Qwen3 Technical Report

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-07T00:53:26.396889Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8c59067-9b43-41a9-827c-b8bc34e76d2c · outbound

This paper cites an unresolved cited work.

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation Unresolved cited work

Reference 49

Resolution: unresolved; raw_fallback, observed 2026-08-07T00:53:28.391316Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation a4c28373-a651-4938-9825-2c2d1a9eab6a · outbound

This paper cites an unresolved cited work.

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation Unresolved cited work

Reference 50

Resolution: unresolved; raw_fallback, observed 2026-08-07T00:53:28.263257Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation f8c50b9b-211f-46ca-84fe-a49eb6ba3671 · outbound

This paper cites an unresolved cited work.

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation Unresolved cited work

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-07T00:53:26.601796Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23a7f921-7928-40aa-ac95-d44eb8f234e0 · outbound

This paper cites an unresolved cited work.

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation Unresolved cited work

Reference 52

Resolution: unresolved; raw_fallback, observed 2026-08-07T00:53:28.096789Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.

Observation 9e854e35-f40b-496e-bb4a-d7f9c37fd5d1 · outbound

This paper cites an unresolved cited work.

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation Unresolved cited work

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-07T00:53:26.788670Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e90e38c3-498d-4f73-a74f-53f56c143979 · outbound

This paper cites Cross-modal Information Flow in Multimodal Large Language Models.

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation Cross-modal Information Flow in Multimodal Large Language Models

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-07T00:53:26.857624Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 712f8acc-f2d9-4f5e-a1d2-08fc799d6f78 · outbound

This paper cites VARGPT: Unified Understanding and Generation in a Visual Autoregressive Multimodal Large Language Model.

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation VARGPT: Unified Understanding and Generation in a Visual Autoregressive Multimodal Large Language Model

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-07T00:53:26.930717Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a285e31-6ff6-44a6-83f3-f8e58b735e75 · outbound

This paper cites VASparse: Towards Efficient Visual Hallucination Mitigation via Visual-Aware Token Sparsification.

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation VASparse: Towards Efficient Visual Hallucination Mitigation via Visual-Aware Token Sparsification

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-07T00:53:27.008416Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f1b04cf-2965-4e64-899b-46dc4a65dddb · outbound

This paper cites Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal Large Language Models.

Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal Large Language Models

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-07T00:53:27.104761Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation d86af2f0-80d8-4cce-a38b-998586743f96 · inbound

C-PTQ: Fisher-weighted Channel-wise Sensitivity for Post-training Quantization of MLLMs cites this paper.

C-PTQ: Fisher-weighted Channel-wise Sensitivity for Post-training Quantization of MLLMs Not All Tokens and Heads Are Equally Important: Dual-Level Attention Intervention for Hallucination Mitigation

Reference 98

Resolution: unresolved; no resolver link, observed 2026-08-01T08:35:58.508826Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.