Paper Citation Record · LEDGER

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens

As of 21 August 2026, this Paper Citation Record lists 54 of 54 outbound references and 11 inbound Pith citation observations for arXiv:2411.16724.

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

pith.paper-citation-record.v1
2411.16724 v3

Coverage vector

measured 54 of 54 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-12T14:23:24.441731Z

measured 65 of 65 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+00:00

measured 11 of 11 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-12T16:31:12.955079Z

measured 1 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

54 of 54 outbound references displayed

verified exact0
verified fuzzy25
unresolved28
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation aaaa354a-858d-4d71-9e91-f972a05edc8a · outbound

This paper cites Behind the scene: Revealing the secrets of pre-trained vision-and-language models.

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens Behind the scene: Revealing the secrets of pre-trained vision-and-language models

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:23:26.931946Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 0e065319-1e87-418c-890e-8b64f222ae41 · outbound

This paper cites An empirical study of clip for text-based person search.

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens An empirical study of clip for text-based person search

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:23:26.847175Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation a79252ba-2080-47e5-a520-e92671985df4 · outbound

This paper cites Generic attention- model explainability for interpreting bi-modal and encoder- decoder transformers.

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens Generic attention- model explainability for interpreting bi-modal and encoder- decoder transformers

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-12T14:23:22.929183Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67689903-e631-4523-97aa-f69540f65d48 · outbound

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

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-12T14:23:22.973605Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d361844-83f5-4a29-a00a-f433b5e5ee72 · outbound

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

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-12T14:23:23.016337Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52f553b1-b307-4f17-85d0-c18b2dad2ee1 · outbound

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

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:23:26.764314Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation dcc839ab-7c49-4a35-83c5-f97c7d31e5c3 · outbound

This paper cites A survey on multimodal large lan- guage models for autonomous driving.

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens A survey on multimodal large lan- guage models for autonomous driving

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-12T14:23:23.104488Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f75f9b39-5bca-412a-935c-9c43176990be · outbound

This paper cites Eva: Exploring the limits of masked visual representa- tion learning at scale.

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens Eva: Exploring the limits of masked visual representa- tion learning at scale

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:23:26.721630Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 4493148e-140d-4a18-a3aa-c04e0a21cf72 · outbound

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

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens Multi-modal hal- lucination control by visual information grounding

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-12T14:23:23.155820Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 554393b9-4bba-4c7f-8558-1d4e69231cf7 · outbound

This paper cites Efros, and Jacob Steinhardt.

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens Efros, and Jacob Steinhardt

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:23:26.634964Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 3f6c2890-1f13-4c63-b240-36e93cb34279 · outbound

This paper cites Transformer feed-forward layers build predictions by pro- moting concepts in the vocabulary space.

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens Transformer feed-forward layers build predictions by pro- moting concepts in the vocabulary space

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:23:26.587386Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 4cbfe42c-81dc-40b7-bd1b-ff0261b85136 · outbound

This paper cites Dissecting recall of factual associations in auto- regressive language models.

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens Dissecting recall of factual associations in auto- regressive language models

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:23:26.576162Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 22fb7ea8-5318-4e56-89fa-9e16624ff83e · outbound

This paper cites Patchscopes: A unifying frame- work for inspecting hidden representations of language mod- els.

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens Patchscopes: A unifying frame- work for inspecting hidden representations of language mod- els

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:23:26.466826Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 5b3b09da-9d8a-4f25-81ed-d35449fc340a · outbound

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

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens Detecting and preventing hallucinations in large vision language models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-12T14:23:23.201236Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b1bf9fb-3522-4e5b-b591-226cffa10548 · outbound

This paper cites Scaling New Frontiers: Insights into Large Recommendation Models.

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens Scaling New Frontiers: Insights into Large Recommendation Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-12T14:23:23.224951Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2fe9b84-7a4e-4ad5-a5cc-5744999b6bfb · outbound

This paper cites Overthinking the truth: Understanding how language models process false demonstrations.

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens Overthinking the truth: Understanding how language models process false demonstrations

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:23:26.320130Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 6c14cb15-0ae1-4ea3-be84-e599ef37a040 · outbound

This paper cites Llm factoscope: Uncovering llms’ factual discernment through measuring inner states.

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens Llm factoscope: Uncovering llms’ factual discernment through measuring inner states

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:23:26.226572Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 56abdca3-c773-41d8-bfd3-211bb8bd0140 · outbound

This paper cites Geometric vi- sual similarity learning in 3d medical image self-supervised pre-training.

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens Geometric vi- sual similarity learning in 3d medical image self-supervised pre-training

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:23:26.164454Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation fa7b7721-d356-4415-8a87-297cc2a7645f · outbound

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

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens Opera: Alleviating hallucination in multi- modal large language models via over-trust penalty and retrospection-allocation

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:23:26.091743Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation ab638459-fed7-4cde-b3b2-3cb5c5fcacd6 · outbound

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

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens Hallucination augmented contrastive learn- ing for multimodal large language model

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-12T14:23:23.410521Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a068e6fe-cd88-4107-ba59-448817303d24 · outbound

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

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens Interpreting and Editing Vision-Language Representations to Mitigate Hallucinations

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-12T14:23:23.424231Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02332793-4ef9-473c-8ca8-27ced28d1c37 · outbound

This paper cites Adam: A Method for Stochastic Optimization.

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens Adam: A Method for Stochastic Optimization

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-12T14:23:23.431909Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f1a24f4a-a0cb-47d3-bc27-ee0a88604cb3 · outbound

This paper cites Multi-scale spatial-temporal attention networks for functional connectome classification.

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens Multi-scale spatial-temporal attention networks for functional connectome classification

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:23:25.931575Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation ec885e99-09f9-42c6-b321-ca0043f97478 · outbound

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

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens Mitigating object hal- lucinations in large vision-language models through visual contrastive decoding

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:23:25.878399Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation ee7e8419-60d1-42f2-9544-98ac18e18496 · outbound

This paper cites Microsoft coco: Common objects in context.

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens Microsoft coco: Common objects in context

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-12T14:23:23.553337Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ee2ccbbc-1801-43d1-9bef-b82c0df41ea4 · outbound

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

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens Mitigating hallucination in large multi-modal models via robust instruction tuning

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:23:25.699997Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation f20ad999-c220-425d-ac09-a8144e3c9da0 · outbound

This paper cites Improved baselines with visual instruction tuning.

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens Improved baselines with visual instruction tuning

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-12T14:23:23.594888Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ae84472-b523-4d0d-a13d-cf8ab98fe1b4 · outbound

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

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens Paying More Attention to Image: A Training-Free Method for Alleviating Hallucination in LVLMs

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-12T14:23:23.612147Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d35e725-ed9d-453b-b1a6-d01ff62323b7 · outbound

This paper cites Interpreting gpt: The logit lens.

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens Interpreting gpt: The logit lens

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:23:25.542355Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 3d7559ba-ac93-4d98-b529-b2e85cd58530 · outbound

This paper cites Towards vision-language mechanistic interpretabil- ity: A causal tracing tool for blip.

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens Towards vision-language mechanistic interpretabil- ity: A causal tracing tool for blip

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-12T14:23:23.698779Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e657c38f-9a23-4c4b-99c8-5df856ed30c5 · outbound

This paper cites A Concept-Based Explainability Framework for Large Multimodal Models.

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens A Concept-Based Explainability Framework for Large Multimodal Models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-12T14:23:23.764331Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50a00c62-011b-42ac-9204-bbdb2d5222c9 · outbound

This paper cites LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL.

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-12T14:23:23.814252Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40b807b2-1a29-404e-b850-b8a3df7db4cd · outbound

This paper cites Learn- ing transferable visual models from natural language super- vision.

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens Learn- ing transferable visual models from natural language super- vision

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-12T14:23:23.861150Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa21dcf9-1ca7-4017-bfef-12aa139c45be · outbound

This paper cites Object hallucination in image captioning.

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens Object hallucination in image captioning

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:23:25.372326Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 8f7dd588-174c-449d-adf8-5a38bc4ec9dc · outbound

This paper cites Optimizing Sequential Recommendation Models with Scaling Laws and Approximate Entropy.

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens Optimizing Sequential Recommendation Models with Scaling Laws and Approximate Entropy

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-12T14:23:23.905570Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d481232f-92ff-4bb3-8e37-92ab2d8fb918 · outbound

This paper cites Unsupervised Real-Time Hallucination Detection based on the Internal States of Large Language Models.

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens Unsupervised Real-Time Hallucination Detection based on the Internal States of Large Language Models

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-12T14:23:23.920988Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb96f49e-b2e8-4aaa-abe6-63577ff9c24e · outbound

This paper cites an unresolved cited work.

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens Unresolved cited work

Reference 37

Resolution: unresolved; raw_fallback, observed 2026-08-12T14:23:25.288769Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation fef20a19-7858-41dd-910a-df9072f8c5f3 · outbound

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

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens LLaMA: Open and Efficient Foundation Language Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-12T14:23:23.939179Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8de7e1d-a69d-4588-a4e8-a7dd286be116 · outbound

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

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-12T14:23:23.981307Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 577d09ba-a117-4007-b5b0-01a98170bae8 · outbound

This paper cites Attention is all you need.

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens Attention is all you need

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:23:25.231167Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 5c5a0beb-9028-45fb-aa37-c21561ac2224 · outbound

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

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens AMBER: An LLM-free Multi-dimensional Benchmark for MLLMs Hallucination Evaluation

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-12T14:23:24.086413Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 523bee1e-1fe3-4850-8fe8-ba81e14c377d · outbound

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

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens Mitigating Hallucinations in Large Vision-Language Models with Instruction Contrastive Decoding

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-12T14:23:24.120460Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6b9406f-8c12-4555-8b49-eae4f102bb1a · outbound

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

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens Logical Closed Loop: Uncovering Object Hallucinations in Large Vision-Language Models

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-12T14:23:24.174469Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89b4f003-0308-4cae-9e52-732f204bb713 · outbound

This paper cites A Survey on Multimodal Large Language Models.

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens A Survey on Multimodal Large Language Models

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-12T14:23:24.195905Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a44c815-8c47-4c0f-8f6f-456f11612981 · outbound

This paper cites Woodpecker: Hallucination correction for multimodal large language models.

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens Woodpecker: Hallucination correction for multimodal large language models

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:23:25.213677Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 3412e0bd-e56b-4edd-929f-0eef3a80f9b5 · outbound

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

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens Hallucidoctor: Mitigating hallucinatory toxicity in visual instruction data

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:23:25.118872Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 9e5f018a-cfa4-4a73-8ef1-119639a74bbd · outbound

This paper cites Attention satisfies: A constraint- satisfaction lens on factual errors of language models.

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens Attention satisfies: A constraint- satisfaction lens on factual errors of language models

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:23:25.061150Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation b2015720-3e37-4761-8ea8-9160a91e8ce8 · outbound

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

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens HallE-Control: Controlling Object Hallucination in Large Multimodal Models

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-12T14:23:24.230917Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5836a039-8e84-4e7b-8582-604a477f2eec · outbound

This paper cites Wings: Learning multimodal llms without text-only forgetting.

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens Wings: Learning multimodal llms without text-only forgetting

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:23:24.973134Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation e1f83bc1-1bde-46f8-a754-233d9f2cc601 · outbound

This paper cites Mitigating Object Hallucination in Large Vision-Language Models via Image-Grounded Guidance.

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens Mitigating Object Hallucination in Large Vision-Language Models via Image-Grounded Guidance

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-12T14:23:24.313664Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6acc91f7-2d50-43d6-84d2-837267a3dfc3 · outbound

This paper cites Harmonizing visual text comprehension and gen- eration.

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens Harmonizing visual text comprehension and gen- eration

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:23:24.901203Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 1a23b6c4-dd79-44e2-b262-aee3e2e72e85 · outbound

This paper cites Analyzing and mitigating object hallucination in large vision-language models.

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens Analyzing and mitigating object hallucination in large vision-language models

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:23:24.867324Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 5226c4c5-8129-4a77-84de-a3862fd3f3c4 · outbound

This paper cites Debiased fine-tuning for vision-language models by prompt regularization.

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens Debiased fine-tuning for vision-language models by prompt regularization

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-12T14:23:24.783772Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 2bab508a-9c9d-4225-a1e0-bfb0b6e33e07 · outbound

This paper cites bicycle”“traffic lights.

Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens bicycle”“traffic lights

Reference 54

Resolution: malformed identifier; raw_fallback, observed 2026-08-12T14:23:24.728502Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Pith citing papers

Observation 0d31e5fd-2734-4a17-b51e-1d22a8f52548 · inbound

Visual Attention Never Fades: Selective Progressive Attention ReCalibration for Detailed Image Captioning in Multimodal Large Language Models cites this paper.

Visual Attention Never Fades: Selective Progressive Attention ReCalibration for Detailed Image Captioning in Multimodal Large Language Models Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-09T15:26:18.828246Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27e3db79-4f22-4ca6-9cad-af91b5866b2b · inbound

CLAIM: Mitigating Multilingual Object Hallucination in Large Vision-Language Models with Cross-Lingual Attention Intervention cites this paper.

CLAIM: Mitigating Multilingual Object Hallucination in Large Vision-Language Models with Cross-Lingual Attention Intervention Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T11:22:38.815007Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a485711-a658-4265-8685-3089ac696e31 · inbound

Energy-Guided Decoding for Object Hallucination Mitigation cites this paper.

Energy-Guided Decoding for Object Hallucination Mitigation Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T18:39:27.700032Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 235586a9-09bb-4037-b1d9-882a2f8f9c89 · inbound

Modality Bias in LVLMs: Analyzing and Mitigating Object Hallucination via Attention Lens cites this paper.

Modality Bias in LVLMs: Analyzing and Mitigating Object Hallucination via Attention Lens Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T05:04:23.314967Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56fe9606-cbb1-4eb2-9601-588ed72eff14 · inbound

SAVER: Mitigating Hallucinations in Large Vision-Language Models via Style-Aware Visual Early Revision cites this paper.

SAVER: Mitigating Hallucinations in Large Vision-Language Models via Style-Aware Visual Early Revision Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-06T04:42:37.262710Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3081177e-7ba2-4319-b1bf-aeecfdc0d251 · inbound

Why and When Visual Token Pruning Fails? A Study on Relevant Visual Information Shift in MLLMs Decoding cites this paper.

Why and When Visual Token Pruning Fails? A Study on Relevant Visual Information Shift in MLLMs Decoding Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-11T11:31:01.421189Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation b7a277c3-88e9-4bd0-a5dd-728fa86507e8 · inbound

HypEHR: Hyperbolic Modeling of Electronic Health Records for Efficient Question Answering cites this paper.

HypEHR: Hyperbolic Modeling of Electronic Health Records for Efficient Question Answering Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens

Reference 276

Resolution: verified exact; arxiv_id, observed 2026-05-09T23:54:45.676745Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 0a6210a5-fcc6-462a-be07-c6a7766504ef · inbound

Grounded or Guessing? LVLM Confidence Estimation via Blind-Image Contrastive Ranking cites this paper.

Grounded or Guessing? LVLM Confidence Estimation via Blind-Image Contrastive Ranking Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:46:47.139577Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 6edd1f80-e02e-4c04-9c09-1b61a8c3abc0 · inbound

Grounded or Guessing? LVLM Confidence Estimation via Blind-Image Contrastive Ranking cites this paper.

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-05-19T17:12:41.136474Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 6c8b6a24-f2ca-453a-b294-e6c1cd764c2d · inbound

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

Verbalizable Representations Form a Global Workspace in Language Models Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:25.901469Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74dc4d7c-40cd-4536-8115-69dd3629a0bc · inbound

UniProbe: A Learnable Token-Level Hallucination Detector for Large VLMs using Multi-Structural Internal Representations cites this paper.

UniProbe: A Learnable Token-Level Hallucination Detector for Large VLMs using Multi-Structural Internal Representations Devils in Middle Layers of Large Vision-Language Models: Interpreting, Detecting and Mitigating Object Hallucinations via Attention Lens

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-12T16:31:12.955079Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.