Paper Citation Record · LEDGER

Can VLMs Truly Forget? Benchmarking Training-Free Visual Concept Unlearning

As of 4 August 2026, this Paper Citation Record lists 15 of 15 outbound references and 0 inbound Pith citation observations for arXiv:2604.03114.

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

pith.paper-citation-record.v1
2604.03114 v1

Coverage vector

measured 15 of 15 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-13T19:48:03.278822Z

measured 15 of 15 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-04T06:34:03.388597+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

15 of 15 outbound references displayed

verified exact9
verified fuzzy2
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch4

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 69dac1c6-cdd3-4c8d-9e9d-43c5ff245eb3 · outbound

This paper cites Qwen3-VL Technical Report.

Can VLMs Truly Forget? Benchmarking Training-Free Visual Concept Unlearning Qwen3-VL Technical Report

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-05-13T19:48:11.155159Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 02670e42-bf9b-469e-abe2-dd2729df11e0 · outbound

This paper cites Towards making systems forget with machine unlearning.

Can VLMs Truly Forget? Benchmarking Training-Free Visual Concept Unlearning Towards making systems forget with machine unlearning

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T19:48:11.886072Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 12df25bd-939d-44a5-8f95-711e7877684e · outbound

This paper cites Do More Details Always Introduce More Hallucinations in LVLM-based Image Captioning?.

Can VLMs Truly Forget? Benchmarking Training-Free Visual Concept Unlearning Do More Details Always Introduce More Hallucinations in LVLM-based Image Captioning?

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-13T19:48:11.167346Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation df58f1b9-6555-4f15-b72c-53290881ab3d · outbound

This paper cites LLaVA-OneVision: Easy Visual Task Transfer.

Can VLMs Truly Forget? Benchmarking Training-Free Visual Concept Unlearning LLaVA-OneVision: Easy Visual Task Transfer

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-05-13T19:48:11.157727Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 86b887aa-8a4d-4380-87ec-3a220f01d122 · outbound

This paper cites TOFU: A Task of Fictitious Unlearning for LLMs.

Can VLMs Truly Forget? Benchmarking Training-Free Visual Concept Unlearning TOFU: A Task of Fictitious Unlearning for LLMs

Reference 5

Resolution: verified exact; arxiv_id, observed 2026-05-16T11:07:39.404904Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 813fd136-d5b2-4b7c-8241-e94a88de600c · outbound

This paper cites SmolVLM: Redefining small and efficient multimodal models.

Can VLMs Truly Forget? Benchmarking Training-Free Visual Concept Unlearning SmolVLM: Redefining small and efficient multimodal models

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-05-13T20:23:51.804797Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 9a4fdc75-73f2-4551-88cc-2e8b6bef355b · outbound

This paper cites In-Context Unlearning: Language Models as Few Shot Unlearners.

Can VLMs Truly Forget? Benchmarking Training-Free Visual Concept Unlearning In-Context Unlearning: Language Models as Few Shot Unlearners

Reference 7

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T19:48:11.161618Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 8481e362-c866-4789-bb18-144ca51a1323 · outbound

This paper cites MUSE: Machine Unlearning Six-Way Evaluation for Language Models.

Can VLMs Truly Forget? Benchmarking Training-Free Visual Concept Unlearning MUSE: Machine Unlearning Six-Way Evaluation for Language Models

Reference 8

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T19:48:11.175802Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation f20e8317-b09d-4a39-b103-3214e54fc13b · outbound

This paper cites Guardrail Baselines for Unlearning in LLMs.

Can VLMs Truly Forget? Benchmarking Training-Free Visual Concept Unlearning Guardrail Baselines for Unlearning in LLMs

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-13T19:48:11.186927Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 30241674-1438-43d0-b162-31684fd7f3bc · outbound

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

Can VLMs Truly Forget? Benchmarking Training-Free Visual Concept Unlearning Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-05-13T19:48:11.184077Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation f3273257-359f-4029-b1ac-0c4a6b2a41a5 · outbound

This paper cites AID: A Benchmark Dataset for Performance Evaluation of Aerial Scene Classification.

Can VLMs Truly Forget? Benchmarking Training-Free Visual Concept Unlearning AID: A Benchmark Dataset for Performance Evaluation of Aerial Scene Classification

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-13T19:48:11.170191Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation a984be64-eca3-412b-9df6-7fb35f0d700b · outbound

This paper cites When and why vision-language models behave like bags-of-words, and what to do about it?.

Can VLMs Truly Forget? Benchmarking Training-Free Visual Concept Unlearning When and why vision-language models behave like bags-of-words, and what to do about it?

Reference 12

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T19:48:11.172994Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation c88f045b-b0bf-4adc-8807-714f44e7571d · outbound

This paper cites Treat Visual Tokens as Text? But Your MLLM Only Needs Fewer Efforts to See.

Can VLMs Truly Forget? Benchmarking Training-Free Visual Concept Unlearning Treat Visual Tokens as Text? But Your MLLM Only Needs Fewer Efforts to See

Reference 13

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T19:48:11.181219Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 3c4b5d9a-f7d8-4d28-9391-f061711af6a6 · outbound

This paper cites InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models.

Can VLMs Truly Forget? Benchmarking Training-Free Visual Concept Unlearning InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models

Reference 14

Resolution: verified exact; local_arxiv, observed 2026-05-13T19:48:11.178650Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation cf8f3767-2d64-4dc3-b500-c5303a255e40 · outbound

This paper cites A Complete experimental results Table 3: Combined results on AID, Celebrity, COCO, LAD-Color, LAD-Habitat, Logo2K+, MIT Indoor67, and SpatialMQA.

Can VLMs Truly Forget? Benchmarking Training-Free Visual Concept Unlearning A Complete experimental results Table 3: Combined results on AID, Celebrity, COCO, LAD-Color, LAD-Habitat, Logo2K+, MIT Indoor67, and SpatialMQA

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T19:48:11.887988Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Pith citing papers

No inbound Pith citation observations are available.