Paper Citation Record · LEDGER

Rethinking Explainability in the Era of Multimodal AI

As of 14 August 2026, this Paper Citation Record lists 69 of 69 outbound references and 5 inbound Pith citation observations for arXiv:2506.13060.

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

pith.paper-citation-record.v1
2506.13060 v1

Coverage vector

measured 69 of 69 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T00:42:29.029561Z

measured 74 of 74 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-14T06:32:32.682623+00:00

measured 5 of 5 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T00:02:59.058102Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-02T01:56:27.425584Z

Reference resolution

69 of 69 outbound references displayed

verified exact1
verified fuzzy61
unresolved7
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 3af1c08a-96a0-4a21-a3c9-502787544d37 · outbound

This paper cites Phi-3 technical report: A highly capable language model locally on your phone.

Rethinking Explainability in the Era of Multimodal AI Phi-3 technical report: A highly capable language model locally on your phone

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:42:29.662053Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e9e195e2-7211-4c68-b92a-70e74d175dd7 · outbound

This paper cites Explaining image classifiers by removing input features using generative models.

Rethinking Explainability in the Era of Multimodal AI Explaining image classifiers by removing input features using generative models

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:42:29.654111Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 984070d2-2f36-4156-8336-e40bc6dbc97f · outbound

This paper cites Rethinking stability for attribution-based explanations.

Rethinking Explainability in the Era of Multimodal AI Rethinking stability for attribution-based explanations

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:42:29.646503Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation dac50e95-3d98-4e19-9891-d72c32325bb1 · outbound

This paper cites Openxai: Towards a transparent evaluation of model explanations.

Rethinking Explainability in the Era of Multimodal AI Openxai: Towards a transparent evaluation of model explanations

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:42:29.637512Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation ba26f6be-8964-426e-ac0a-ff778ea3e087 · outbound

This paper cites Probing gnn explainers: A rigorous theoretical and empirical analysis of gnn explanation methods.

Rethinking Explainability in the Era of Multimodal AI Probing gnn explainers: A rigorous theoretical and empirical analysis of gnn explanation methods

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:42:29.629456Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 0d929ea4-407b-42d5-b2ee-e84abde6576f · outbound

This paper cites Evaluating explainability for graph neural networks.

Rethinking Explainability in the Era of Multimodal AI Evaluating explainability for graph neural networks

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:42:29.621237Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 68a648b3-10ac-47c0-9a67-1d34044f88a8 · outbound

This paper cites Faithfulness vs.

Rethinking Explainability in the Era of Multimodal AI Faithfulness vs

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:42:29.613439Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e80cc26b-6ede-4b8c-b393-ea0cbb901c9f · outbound

This paper cites On the robustness of interpretability methods.

Rethinking Explainability in the Era of Multimodal AI On the robustness of interpretability methods

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:42:29.605272Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 2bfe0cc6-178d-49d3-830a-23b811035518 · outbound

This paper cites an unresolved cited work.

Rethinking Explainability in the Era of Multimodal AI Unresolved cited work

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T00:42:26.788163Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b30ca549-e23c-44cd-b4d1-2a5e5bf906ef · outbound

This paper cites Bottom-up and top-down attention for image captioning and visual question answering.

Rethinking Explainability in the Era of Multimodal AI Bottom-up and top-down attention for image captioning and visual question answering

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T00:42:26.837211Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b72fe31-4c9f-41bd-a6f8-07b01590d325 · outbound

This paper cites Mechanistic interpretability for ai safety--a review.

Rethinking Explainability in the Era of Multimodal AI Mechanistic interpretability for ai safety--a review

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:42:29.586577Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e9b0ca62-89ea-4dad-96fa-822135289895 · outbound

This paper cites Interpreting clip with sparse linear concept embeddings (splice).

Rethinking Explainability in the Era of Multimodal AI Interpreting clip with sparse linear concept embeddings (splice)

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:42:29.578548Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 9330670c-f551-4adf-8165-41ac0533e532 · outbound

This paper cites A systematic review of natural language processing applied to radiology reports.

Rethinking Explainability in the Era of Multimodal AI A systematic review of natural language processing applied to radiology reports

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:42:29.570777Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 71c8d4e4-7cbe-4f11-8b8a-63ddd07767e2 · outbound

This paper cites Fleurs: Few-shot learning evaluation of universal representations of speech.

Rethinking Explainability in the Era of Multimodal AI Fleurs: Few-shot learning evaluation of universal representations of speech

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:42:29.562133Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation ff5ae73b-a5ee-420c-80b2-f58a98d2e890 · outbound

This paper cites Sparse autoencoders find highly interpretable features in language models.

Rethinking Explainability in the Era of Multimodal AI Sparse autoencoders find highly interpretable features in language models

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:42:29.552564Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation b83aca68-c528-4830-a315-44dc01d2732c · outbound

This paper cites A survey of the state of explainable AI for natural language processing.

Rethinking Explainability in the Era of Multimodal AI A survey of the state of explainable AI for natural language processing

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:42:29.543988Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 5c4b732f-1d9d-44a5-a94e-5e23da05d5cc · outbound

This paper cites Interpretable explanations of black boxes by meaningful perturbation.

Rethinking Explainability in the Era of Multimodal AI Interpretable explanations of black boxes by meaningful perturbation

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:42:29.535889Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation dd7c68a8-f836-4f07-8ee9-9d1bc5b81bec · outbound

This paper cites Attention in natural language processing.

Rethinking Explainability in the Era of Multimodal AI Attention in natural language processing

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:42:29.526672Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 2a22c5e4-73e5-4af5-8ac1-aa13a8c52e87 · outbound

This paper cites Scaling and evaluating sparse autoencoders.

Rethinking Explainability in the Era of Multimodal AI Scaling and evaluating sparse autoencoders

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T00:42:27.877776Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73110066-299b-41a0-a5ba-3a79da32cd2b · outbound

This paper cites Multimodal neurons in artificial neural networks.

Rethinking Explainability in the Era of Multimodal AI Multimodal neurons in artificial neural networks

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T00:42:28.022494Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01ec86a9-f872-4637-8b6e-28f5d28e6f45 · outbound

This paper cites Localizing model behavior with path patching.

Rethinking Explainability in the Era of Multimodal AI Localizing model behavior with path patching

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:42:29.513201Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 58b5f494-cf54-4156-b688-bddedc945355 · outbound

This paper cites circuit-tracer.

Rethinking Explainability in the Era of Multimodal AI circuit-tracer

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:42:29.505128Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 53e35e70-3a07-4041-b1ee-a02db5051133 · outbound

This paper cites Sparse autoencoders can interpret randomly initialized transformers.

Rethinking Explainability in the Era of Multimodal AI Sparse autoencoders can interpret randomly initialized transformers

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:42:29.497397Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 27fa1c05-ccfb-4f74-8987-727c3b9967ea · outbound

This paper cites How to use and interpret activation patching.

Rethinking Explainability in the Era of Multimodal AI How to use and interpret activation patching

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:42:29.488734Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 8e6f692f-2762-40d5-ae90-1f88b12c21d3 · outbound

This paper cites Gpt-4o system card.

Rethinking Explainability in the Era of Multimodal AI Gpt-4o system card

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:42:29.481319Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation f0aa6866-6edb-45d1-8aac-b804a1dcec0c · outbound

This paper cites Attention is not explanation.

Rethinking Explainability in the Era of Multimodal AI Attention is not explanation

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:42:29.473645Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e97b0d30-c973-4b55-97ee-35d444b68328 · outbound

This paper cites Towards better explanations of class activation mapping.

Rethinking Explainability in the Era of Multimodal AI Towards better explanations of class activation mapping

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:42:29.465422Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 1658005b-6abd-4e3c-b28c-f6c0d9339249 · outbound

This paper cites See what you are told: Visual attention sink in large multimodal models.

Rethinking Explainability in the Era of Multimodal AI See what you are told: Visual attention sink in large multimodal models

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:42:29.456805Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation b55d8e19-e710-4b8d-b0eb-24b3e9c61569 · outbound

This paper cites Are sparse autoencoders useful? a case study in sparse probing.

Rethinking Explainability in the Era of Multimodal AI Are sparse autoencoders useful? a case study in sparse probing

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:42:29.448113Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 76fd0b06-a54c-44fd-9a18-11a8cf2a2735 · outbound

This paper cites Interpretability beyond feature attribution: Quantitative testing with concept activation vectors (tcav).

Rethinking Explainability in the Era of Multimodal AI Interpretability beyond feature attribution: Quantitative testing with concept activation vectors (tcav)

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:42:29.440079Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation a232f5b8-1e45-4dac-84d1-b0de4c5a8ee9 · outbound

This paper cites Visual explanations from hadamard product in multimodal deep networks.

Rethinking Explainability in the Era of Multimodal AI Visual explanations from hadamard product in multimodal deep networks

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:42:29.432182Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 2663b66b-3d31-4647-8e56-29db4b1ea64f · outbound

This paper cites Sparse autoencoders work on attention layer outputs.

Rethinking Explainability in the Era of Multimodal AI Sparse autoencoders work on attention layer outputs

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:42:29.423738Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation fc111ff6-7041-490a-8150-c998f73b5d88 · outbound

This paper cites Concept bottleneck models.

Rethinking Explainability in the Era of Multimodal AI Concept bottleneck models

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:42:29.415774Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation d31aee84-5f77-4372-9004-bce8dda6e587 · outbound

This paper cites an unresolved cited work.

Rethinking Explainability in the Era of Multimodal AI Unresolved cited work

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T00:42:28.919086Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd86b7aa-387b-4539-ae63-b27b6d14e43f · outbound

This paper cites The llama 4 herd: The beginning of a new era of natively multimodal ai innovation, 2025.

Rethinking Explainability in the Era of Multimodal AI The llama 4 herd: The beginning of a new era of natively multimodal ai innovation, 2025

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:42:29.400086Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 6d72c13d-9cff-4836-9bb7-9c180aaa53c7 · outbound

This paper cites Dime: Fine-grained interpretations of multimodal models via disentangled local explanations.

Rethinking Explainability in the Era of Multimodal AI Dime: Fine-grained interpretations of multimodal models via disentangled local explanations

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:42:29.390166Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 10a7cc3b-7dee-47f0-864b-c2bffc8d1be5 · outbound

This paper cites Towards principled evaluations of sparse autoencoders for interpretability and control.

Rethinking Explainability in the Era of Multimodal AI Towards principled evaluations of sparse autoencoders for interpretability and control

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:42:29.381270Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 09701853-acbf-4520-982b-17a8998c66c5 · outbound

This paper cites K-sparse autoencoders.

Rethinking Explainability in the Era of Multimodal AI K-sparse autoencoders

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:42:29.372416Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation d948b4a3-5d6f-45b6-97ac-3399c09cfbb4 · outbound

This paper cites Cora Dataset , 2017.

Rethinking Explainability in the Era of Multimodal AI Cora Dataset , 2017

Reference 39

Resolution: verified exact; doi, observed 2026-08-07T00:42:29.058540Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 6ad8b818-4dd1-44e7-956b-8b5643d31e81 · outbound

This paper cites Dual attention networks for multimodal reasoning and matching.

Rethinking Explainability in the Era of Multimodal AI Dual attention networks for multimodal reasoning and matching

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:42:29.363261Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation dc8897a5-a6b7-42bc-9794-ba6034848c7b · outbound

This paper cites Attribution patching: Activation patching at industrial scale.

Rethinking Explainability in the Era of Multimodal AI Attribution patching: Activation patching at industrial scale

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:42:29.354495Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 79cae0d2-f3bc-4e66-be53-19e694b72264 · outbound

This paper cites Towards interpreting visual information processing in vision-language models.

Rethinking Explainability in the Era of Multimodal AI Towards interpreting visual information processing in vision-language models

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:42:29.345637Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation c7cbc69e-bf5e-4747-93c9-94786e7f064e · outbound

This paper cites Interpreting gpt: the logit lens — lesswrong, 2020.

Rethinking Explainability in the Era of Multimodal AI Interpreting gpt: the logit lens — lesswrong, 2020

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:42:29.336016Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation d715bbb6-fe3d-4db6-a41c-bd1bd4ebd834 · outbound

This paper cites Sparse autoencoders enable scalable and reliable circuit identification in language models.

Rethinking Explainability in the Era of Multimodal AI Sparse autoencoders enable scalable and reliable circuit identification in language models

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:42:29.323328Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 2c07b905-63f8-44ea-a47f-6437fd125a97 · outbound

This paper cites Orchestrating explainable artificial intelligence for multimodal and longitudinal data in medical imaging.

Rethinking Explainability in the Era of Multimodal AI Orchestrating explainable artificial intelligence for multimodal and longitudinal data in medical imaging

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:42:29.313186Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 4800466b-dc2d-4089-a996-e299c028f495 · outbound

This paper cites Multimodal explanations: Justifying decisions and pointing to the evidence.

Rethinking Explainability in the Era of Multimodal AI Multimodal explanations: Justifying decisions and pointing to the evidence

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:42:29.303136Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 4090a390-ff36-49e6-b878-5d2e5f2043e3 · outbound

This paper cites Perception test: A diagnostic benchmark for multimodal video models.

Rethinking Explainability in the Era of Multimodal AI Perception test: A diagnostic benchmark for multimodal video models

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:42:29.293361Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 5710ee75-fc3d-4db1-b004-49210df59698 · outbound

This paper cites why should i trust you?.

Rethinking Explainability in the Era of Multimodal AI why should i trust you?

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:42:29.283504Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 04b749df-81b9-485d-8747-39cd821ff174 · outbound

This paper cites Multimodal explainable artificial intelligence: A comprehensive review of methodological advances and future research directions.

Rethinking Explainability in the Era of Multimodal AI Multimodal explainable artificial intelligence: A comprehensive review of methodological advances and future research directions

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:42:29.273333Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 4a8f4d6c-f88d-40cb-9d4a-19ca03f09474 · outbound

This paper cites Grad-cam: visual explanations from deep networks via gradient-based localization.

Rethinking Explainability in the Era of Multimodal AI Grad-cam: visual explanations from deep networks via gradient-based localization

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:42:29.262818Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation d47a6440-9889-4321-bc0f-404e956b03d2 · outbound

This paper cites Towards a systematic evaluation of hallucinations in large-vision language models, 2025.

Rethinking Explainability in the Era of Multimodal AI Towards a systematic evaluation of hallucinations in large-vision language models, 2025

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:42:29.251109Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation f7a6c207-7c7d-489a-85ba-61204051517d · outbound

This paper cites A survey on sparse autoencoders: Interpreting the internal mechanisms of large language models.

Rethinking Explainability in the Era of Multimodal AI A survey on sparse autoencoders: Interpreting the internal mechanisms of large language models

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:42:29.240739Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation a04aec4a-c21a-4f5a-9ffe-21c92752d966 · outbound

This paper cites Explain and improve: Lrp-inference fine-tuning for image captioning models.

Rethinking Explainability in the Era of Multimodal AI Explain and improve: Lrp-inference fine-tuning for image captioning models

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:42:29.228568Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation db11ca8e-3712-45e5-9120-7b91e1f67191 · outbound

This paper cites A review of multimodal explainable artificial intelligence: Past, present and future.

Rethinking Explainability in the Era of Multimodal AI A review of multimodal explainable artificial intelligence: Past, present and future

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:42:29.218446Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 9478184d-e968-46cf-8c69-23d1654c5cef · outbound

This paper cites Axiomatic attribution for deep networks.

Rethinking Explainability in the Era of Multimodal AI Axiomatic attribution for deep networks

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-07T00:42:28.983629Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 127be7d0-9987-4a6a-9cd6-4d50222b2310 · outbound

This paper cites Gemini: a family of highly capable multimodal models.

Rethinking Explainability in the Era of Multimodal AI Gemini: a family of highly capable multimodal models

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:42:29.202394Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation a4423586-1adb-4559-a1aa-cd6104720e8d · outbound

This paper cites true features.

Rethinking Explainability in the Era of Multimodal AI true features

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:42:29.192345Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 26f833ad-74c0-4781-a7ba-d512b5e24463 · outbound

This paper cites Interpretable multi-modal hate speech detection.

Rethinking Explainability in the Era of Multimodal AI Interpretable multi-modal hate speech detection

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:42:29.182634Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 13d2d4eb-e3db-46fa-b42e-579c28644c3d · outbound

This paper cites Llms as zero-shot graph learners: Alignment of gnn representations with llm token embeddings.

Rethinking Explainability in the Era of Multimodal AI Llms as zero-shot graph learners: Alignment of gnn representations with llm token embeddings

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:42:29.172041Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation c4f7bf7a-9a19-401a-ad58-5cfb88c2a18e · outbound

This paper cites Interpretability-based multimodal convolutional neural networks for skin lesion diagnosis.

Rethinking Explainability in the Era of Multimodal AI Interpretability-based multimodal convolutional neural networks for skin lesion diagnosis

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:42:29.162541Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 42b9148e-0952-4fb0-ae29-825dcfbe4189 · outbound

This paper cites M2lens: Visualizing and explaining multimodal models for sentiment analysis.

Rethinking Explainability in the Era of Multimodal AI M2lens: Visualizing and explaining multimodal models for sentiment analysis

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:42:29.153262Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation ebc623f6-6642-4b47-9c22-8659859ed20f · outbound

This paper cites Logitlens4llms: Extending logit lens analysis to modern large language models.

Rethinking Explainability in the Era of Multimodal AI Logitlens4llms: Extending logit lens analysis to modern large language models

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:42:29.143582Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 9bbe7916-e983-4faf-8c4e-eee4039a93e8 · outbound

This paper cites Measuring cross-modal interactions in multimodal models.

Rethinking Explainability in the Era of Multimodal AI Measuring cross-modal interactions in multimodal models

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:42:29.133461Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation a6605486-fd69-4385-8619-8359b4bcf3e8 · outbound

This paper cites Attention is not not explanation.

Rethinking Explainability in the Era of Multimodal AI Attention is not not explanation

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-07T00:42:29.012981Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bfc1f85b-657c-45ed-bdd8-e0d36f5b9e19 · outbound

This paper cites Audio-text models do not yet leverage natural language.

Rethinking Explainability in the Era of Multimodal AI Audio-text models do not yet leverage natural language

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:42:29.116161Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 0872db54-30ab-424c-bda3-b1f90a1b4014 · outbound

This paper cites Visual entailment: A novel task for fine-grained image understanding.

Rethinking Explainability in the Era of Multimodal AI Visual entailment: A novel task for fine-grained image understanding

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:42:29.106824Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 09e3969f-c253-407b-9aa3-6b7149e17005 · outbound

This paper cites Gnnexplainer: Generating explanations for graph neural networks.

Rethinking Explainability in the Era of Multimodal AI Gnnexplainer: Generating explanations for graph neural networks

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:42:29.097057Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 1f6d3cff-855f-42a1-9d6c-3a80b1249434 · outbound

This paper cites Towards best practices of activation patching in language models: Metrics and methods.

Rethinking Explainability in the Era of Multimodal AI Towards best practices of activation patching in language models: Metrics and methods

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:42:29.087636Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 595c6cf6-5b44-4e92-9567-798b5846efc9 · outbound

This paper cites Vlm ^ 2 -bench: A closer look at how well vlms implicitly link explicit matching visual cues.

Rethinking Explainability in the Era of Multimodal AI Vlm ^ 2 -bench: A closer look at how well vlms implicitly link explicit matching visual cues

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T00:42:29.076856Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Pith citing papers

Observation 849a45c3-d30a-4246-b015-ef3208f6beeb · inbound

Decoding the Multimodal Maze: A Systematic Review on the Adoption of Explainability in Multimodal Attention-based Models cites this paper.

Decoding the Multimodal Maze: A Systematic Review on the Adoption of Explainability in Multimodal Attention-based Models Rethinking Explainability in the Era of Multimodal AI

Reference 132

Resolution: verified exact; arxiv_id, observed 2026-05-19T00:36:56.258662Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 3f2e7f19-a183-44d1-b173-0ae46d6dd0bc · inbound

Decoding the Multimodal Maze: A Systematic Review on the Adoption of Explainability in Multimodal Attention-based Models cites this paper.

Decoding the Multimodal Maze: A Systematic Review on the Adoption of Explainability in Multimodal Attention-based Models Rethinking Explainability in the Era of Multimodal AI

Reference 132

Resolution: unresolved; no resolver link, observed 2026-08-06T00:02:59.058102Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e959f135-5479-437f-8687-0b2463a80929 · inbound

Measuring Cross-Modal Synergy: A Benchmark for VLM Explainability cites this paper.

Measuring Cross-Modal Synergy: A Benchmark for VLM Explainability Rethinking Explainability in the Era of Multimodal AI

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-05-22T06:06:08.728672Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 7fa8a946-a63e-4618-b93c-fd9082e53411 · inbound

When Graph Tokens Sink: A Mechanistic Analysis of Graph Language Models cites this paper.

When Graph Tokens Sink: A Mechanistic Analysis of Graph Language Models Rethinking Explainability in the Era of Multimodal AI

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-07-02T01:56:27.435247Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 78325e5c-d441-4171-ba4c-b955b76fb338 · inbound

CHARM: Charge Calibration and Acoustic Rescue for LLM-based Multimodal Sarcasm Detection cites this paper.

CHARM: Charge Calibration and Acoustic Rescue for LLM-based Multimodal Sarcasm Detection Rethinking Explainability in the Era of Multimodal AI

Reference 23

Resolution: unresolved; no resolver link, observed 2026-07-14T07:04:04.812401Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.