Paper Citation Record · LEDGER

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering

As of 10 August 2026, this Paper Citation Record lists 47 of 47 outbound references and 20 inbound Pith citation observations for arXiv:2502.03628.

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

pith.paper-citation-record.v1
2502.03628 v2

Coverage vector

measured 47 of 47 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-09T04:22:42.241077Z

measured 67 of 67 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+00:00

measured 20 of 20 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T12:46:58.368000Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-03T10:27:56.148889Z

Reference resolution

47 of 47 outbound references displayed

verified exact0
verified fuzzy13
unresolved34
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 449cdd78-bb9c-45d5-a9b0-b7c3f4507880 · outbound

This paper cites write newline.

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering write newline

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:42.091786Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 682142d1-2c17-4132-b4a0-e1fe3c0ff599 · outbound

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

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:42.096309Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a742f65-4b7d-419b-9455-ebb3e0ce7e12 · outbound

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

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering Hallucination of Multimodal Large Language Models: A Survey

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:42.100110Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7df8a6ac-e2b1-46a7-be7c-5b79f6890974 · outbound

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

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:42.103850Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5fbbfe92-65a8-417c-9000-5d34ef872bc8 · outbound

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

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:42.108062Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd33e61c-2ade-416c-823f-f97149a2cde4 · outbound

This paper cites R., and He, P.

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering R., and He, P

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T04:22:42.583240Z

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 70426efc-5aab-4e4a-b70a-6c8be09de357 · outbound

This paper cites Knowledge neurons in pretrained transformers.

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering Knowledge neurons in pretrained transformers

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:42.115130Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b758b05-c7a9-480c-a1d9-aa449f828b66 · outbound

This paper cites Instruct BLIP : Towards general-purpose vision-language models with instruction tuning.

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering Instruct BLIP : Towards general-purpose vision-language models with instruction tuning

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T04:22:42.575051Z

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 46552345-c61f-44bb-8093-350fb5333e32 · outbound

This paper cites A mathematical framework for transformer circuits.

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering A mathematical framework for transformer circuits

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T04:22:42.566220Z

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 4c18adf8-bd6e-4ce7-a8cc-d474cd3c32f8 · outbound

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

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering Multi-modal hallucination control by visual information grounding

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T04:22:42.557550Z

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 22bc6db8-7b5c-4070-9b3a-771c45a8197a · outbound

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

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:42.128733Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40c6cd49-8306-4d74-8058-b1da80c86801 · outbound

This paper cites Transformer feed-forward layers are key-value memories.

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering Transformer feed-forward layers are key-value memories

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:42.132094Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a4dbc48-2817-4731-80a0-42ce95e7a635 · outbound

This paper cites Interpreting gpt: The logit lens.

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering Interpreting gpt: The logit lens

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T04:22:42.549005Z

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 13438085-51ae-4510-ba29-22bc49bc1a78 · outbound

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

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering Opera: Alleviating hallucination in multi-modal large language models via over-trust penalty and retrospection-allocation

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:42.138294Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 53529a46-a1bd-4cd1-9230-8f908f057b7f · outbound

This paper cites GPT-4o System Card.

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering GPT-4o System Card

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:42.141110Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c03ddb0-6068-40e7-956b-85e3d0af41c2 · outbound

This paper cites Hallucination augmented contrastive learning for multimodal large language model.

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering Hallucination augmented contrastive learning for multimodal large language model

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T04:22:42.535618Z

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 9e9e13f9-5e81-42cb-9dd5-57c8ec44f552 · outbound

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

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering Lisa: Reasoning segmentation via large language model

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:42.147436Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a34196b8-10ed-4f25-a6ea-6f18bfd966dc · outbound

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

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering Mitigating object hallucinations in large vision-language models through visual contrastive decoding

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T04:22:42.522196Z

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 dd5e82ea-0019-45ef-8def-cea952efb46f · outbound

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

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:42.153577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb83a348-ec6d-4243-9c6c-37c7e7017a3c · outbound

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

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering Contrastive Decoding: Open-ended Text Generation as Optimization

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:42.156954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f7e489d-4bc4-4e52-abde-9ee34439335b · outbound

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

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering Evaluating object hallucination in large vision-language models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:42.160081Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32431c63-1315-40da-ac57-6dee84ecf1c0 · outbound

This paper cites Implicit In-context Learning.

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering Implicit In-context Learning

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:42.163022Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8ef7579-b719-4aaa-8ed8-aa47afbc8d3d · outbound

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

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering Video-LLaVA: Learning United Visual Representation by Alignment Before Projection

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:42.166126Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation edec0eb2-37d3-4f3a-ae26-d0212dc031fb · outbound

This paper cites an unresolved cited work.

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering Unresolved cited work

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:42.169644Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 705165c3-21d7-4734-9772-bde810516c1c · outbound

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

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering Mitigating hallucination in large multi-modal models via robust instruction tuning

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T04:22:42.504457Z

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 51bee77d-f5cf-4203-bd63-5aaecef73b1b · outbound

This paper cites an unresolved cited work.

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering Unresolved cited work

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:42.176283Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76abc818-1e22-43f4-8bad-9c4c6245d27e · outbound

This paper cites an unresolved cited work.

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering Unresolved cited work

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:42.179539Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09a41f75-0609-413f-9b9d-2414dbca91c8 · outbound

This paper cites an unresolved cited work.

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering Unresolved cited work

Reference 28

Resolution: unresolved; raw_fallback, observed 2026-08-09T04:22:42.486201Z

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 bdb0a944-8673-4343-a040-b9b198a06b8c · outbound

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

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering A Survey on Hallucination in Large Vision-Language Models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:42.185522Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3cead33f-0ac6-4d55-b72a-29989f9cd232 · outbound

This paper cites In-context vectors: Making in context learning more effective and controllable through latent space steering, 2024 e.

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering In-context vectors: Making in context learning more effective and controllable through latent space steering, 2024 e

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T04:22:42.477468Z

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 1344e082-9a89-4420-94c6-341bad502e53 · outbound

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

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering Reducing Hallucinations in Vision-Language Models via Latent Space Steering

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:42.191488Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e52a971-563a-45ea-a508-3f3e3db598c1 · outbound

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

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering Paying More Attention to Image: A Training-Free Method for Alleviating Hallucination in LVLMs

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:42.194580Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6d4e582-1ea7-4835-9dd0-06e4f6809d03 · outbound

This paper cites Object Hallucination in Image Captioning.

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering Object Hallucination in Image Captioning

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:42.197795Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b173ffc3-2fd3-4803-a360-30bbb851d192 · outbound

This paper cites Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders.

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:42.200920Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b14ea5c-1999-4031-9ab0-4c52e4ccdfd9 · outbound

This paper cites Trusting Your Evidence: Hallucinate Less with Context-aware Decoding.

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering Trusting Your Evidence: Hallucinate Less with Context-aware Decoding

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:42.204650Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3507cd6d-6f75-4d28-ad4d-fe7c63742cbf · outbound

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

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering Aligning Large Multimodal Models with Factually Augmented RLHF

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:42.207737Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2f18d62-6c80-4bee-95f2-0ddd855c6b11 · outbound

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

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering Eyes wide shut? exploring the visual shortcomings of multimodal llms

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:42.211058Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 315c1aa6-e23b-4fd0-a01e-1b97d33ec9f5 · outbound

This paper cites M., Thiergart, L., Udell, D., Leech, G., Mini, U., and MacDiarmid, M.

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering M., Thiergart, L., Udell, D., Leech, G., Mini, U., and MacDiarmid, M

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T04:22:42.463401Z

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 2b7510ae-d2e8-498b-8740-6b8cbaebe4c1 · outbound

This paper cites Label words are anchors: An information flow perspective for understanding in-context learning.

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering Label words are anchors: An information flow perspective for understanding in-context learning

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:42.216796Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3fe9bdc-7764-4723-9f88-6a177a0ba57a · outbound

This paper cites Don't Miss the Forest for the Trees: Attentional Vision Calibration for Large Vision Language Models.

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering Don't Miss the Forest for the Trees: Attentional Vision Calibration for Large Vision Language Models

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:42.219746Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44d7267e-7686-4b17-9200-8ad85171ec12 · outbound

This paper cites Gpt4tools: Teaching large language model to use tools via self-instruction.

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering Gpt4tools: Teaching large language model to use tools via self-instruction

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T04:22:42.454651Z

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 33e46bb6-e6ef-426e-88e6-f66ccd5cfa33 · outbound

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

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering Woodpecker: Hallucination Correction for Multimodal Large Language Models

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:42.225880Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce541731-2e9d-4be7-967e-fc90fdfc5afa · outbound

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

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering Hallucidoctor: Mitigating hallucinatory toxicity in visual instruction data

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T04:22:42.445309Z

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 49b428f6-1ddf-4784-ac33-00a6dcfe5255 · outbound

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

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering Less is More: Mitigating Multimodal Hallucination from an EOS Decision Perspective

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:42.231785Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b61e4a89-7847-4cfe-8ada-448be55228e6 · outbound

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

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering Analyzing and Mitigating Object Hallucination in Large Vision-Language Models

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:42.234781Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19397833-7fcb-4513-888d-72aa595ab732 · outbound

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

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-09T04:22:42.238032Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a85bd13-6f2a-41c3-8ba6-874d5c84985c · outbound

This paper cites J., Wang, Z., Mallen, A., Basart, S., Koyejo, S., Song, D., Fredrikson, M., Kolter, J.

The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering J., Wang, Z., Mallen, A., Basart, S., Koyejo, S., Song, D., Fredrikson, M., Kolter, J

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T04:22:42.435420Z

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.

Pith citing papers

Observation 4ae29dc1-ff06-4d7b-86d6-39e9960412c2 · inbound

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

Hallucination of Multimodal Large Language Models: A Survey The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering

Reference 108

Resolution: verified exact; arxiv_id, observed 2026-05-11T12:33:33.958049Z

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 a6b90a7f-732c-47cb-b351-cabaff831831 · inbound

Qwen Look Again: Guiding Vision-Language Reasoning Models to Re-attention Visual Information cites this paper.

Qwen Look Again: Guiding Vision-Language Reasoning Models to Re-attention Visual Information The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T12:46:58.368000Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6114f00-c053-4fb8-a6a2-cc4b806b3095 · inbound

MCA-LLaVA: Manhattan Causal Attention for Reducing Hallucination in Large Vision-Language Models cites this paper.

MCA-LLaVA: Manhattan Causal Attention for Reducing Hallucination in Large Vision-Language Models The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-06T18:09:07.147109Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9af43e8-bee4-4209-b5f7-5a00dc274fbc · inbound

Adaptive Residual-Update Steering for Low-Overhead Hallucination Mitigation in Large Vision Language Models cites this paper.

Adaptive Residual-Update Steering for Low-Overhead Hallucination Mitigation in Large Vision Language Models The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-21T18:50:30.071256Z

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 b06e4a9a-2ee2-41a2-9e3a-d265978b9ab9 · inbound

From Weights to Activations: Is Steering the Next Frontier of Adaptation? cites this paper.

From Weights to Activations: Is Steering the Next Frontier of Adaptation? The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering

Reference 11

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T12:55:24.636940Z

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 b72afbc3-3a9b-497c-b602-12149dc3d6bf · inbound

Prefill-Time Intervention for Mitigating Hallucination in Large Vision-Language Models cites this paper.

Prefill-Time Intervention for Mitigating Hallucination in Large Vision-Language Models The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-11T23:31:16.411697Z

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 81729e34-700d-4312-a1ca-63362b5c890d · inbound

GEASS: Gated Evidence-Adaptive Selective Caption Trust for Vision-Language Models cites this paper.

GEASS: Gated Evidence-Adaptive Selective Caption Trust for Vision-Language Models The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-11T10:11:15.305337Z

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 aa5d5dfd-891b-48ef-a30b-4f00a89928a0 · inbound

GEASS: Gated Evidence-Adaptive Selective Caption Trust for Vision-Language Models cites this paper.

GEASS: Gated Evidence-Adaptive Selective Caption Trust for Vision-Language Models The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-21T00:43:53.569076Z

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 4525dd70-ab25-4201-932f-a114488f34af · inbound

GEASS: Gated Evidence-Adaptive Selective Caption Trust for Vision-Language Models cites this paper.

GEASS: Gated Evidence-Adaptive Selective Caption Trust for Vision-Language Models The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-07-01T00:35:10.169759Z

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 15b62387-9e85-40c5-8b4e-099a5930f65d · inbound

When Language Overwrites Vision: Over-Alignment and Geometric Debiasing in Vision-Language Models cites this paper.

When Language Overwrites Vision: Over-Alignment and Geometric Debiasing in Vision-Language Models The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-12T00:51:15.365180Z

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 e188070b-23db-4e67-a368-dd00da79d83d · inbound

When Language Overwrites Vision: Over-Alignment and Geometric Debiasing in Vision-Language Models cites this paper.

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-14T21:22:58.978250Z

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 df9bdc51-18a9-489a-b902-1848f86ec933 · inbound

When Language Overwrites Vision: Over-Alignment and Geometric Debiasing in Vision-Language Models cites this paper.

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-19T17:07:41.699515Z

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 8d571455-fc7c-4e9f-97dd-87755810bfa9 · inbound

When Language Overwrites Vision: Over-Alignment and Geometric Debiasing in Vision-Language Models cites this paper.

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-06-30T23:45:08.099607Z

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 d12f69c8-ed66-49a3-8d9e-13f6c7f50613 · inbound

Not Blind but Silenced: Rebalancing Vision and Language via Adversarial Counter-Commonsense Equilibrium cites this paper.

Not Blind but Silenced: Rebalancing Vision and Language via Adversarial Counter-Commonsense Equilibrium The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering

Reference 19

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T05:56:25.166065Z

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 af99778c-aaff-419d-8d9a-33ad658df0af · inbound

Mitigating Object Hallucinations in Vision-Language Models through Region-Aware Attention Recalibration cites this paper.

Mitigating Object Hallucinations in Vision-Language Models through Region-Aware Attention Recalibration The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-06-30T11:44:38.759704Z

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 c69ca4e3-3d89-43ed-b3ea-69562b425b7f · inbound

Steer Where It Matters: Token-Level Visual-Sensitivity Steering for LVLMs Hallucination Mitigation cites this paper.

Steer Where It Matters: Token-Level Visual-Sensitivity Steering for LVLMs Hallucination Mitigation The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-07-02T03:06:29.681408Z

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 7b3976ba-56ce-4ec4-85e4-3d48aca48249 · inbound

MultiToP: Learning to Patch Visual Tokens to Mitigate Hallucinations in Video Large Multimodal Models cites this paper.

MultiToP: Learning to Patch Visual Tokens to Mitigate Hallucinations in Video Large Multimodal Models The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering

Reference 36

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T10:27:56.150307Z

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 a32aa892-fdc7-482e-9a4c-24a01abb9b86 · inbound

FADE: Mitigating Hallucinations by Reducing Language-Prior Dominance in Large Vision-Language Models cites this paper.

FADE: Mitigating Hallucinations by Reducing Language-Prior Dominance in Large Vision-Language Models The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering

Reference 30

Resolution: metadata mismatch; arxiv_id, observed 2026-06-30T07:14:21.522578Z

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 e42ce6cb-66cc-4d37-840d-916e48dcf2cb · inbound

FADE: Mitigating Hallucinations by Reducing Language-Prior Dominance in Large Vision-Language Models cites this paper.

Reference 30

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T20:47:22.345284Z

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 a950bf1c-3c40-4b49-a8c0-077d3819523a · inbound

Verbalizable Representations Form a Global Workspace in Language Models cites this paper.

Verbalizable Representations Form a Global Workspace in Language Models The Hidden Life of Tokens: Reducing Hallucination of Large Vision-Language Models via Visual Information Steering

Reference 105

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:28.935620Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.