Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links
Paper Citation Record · LEDGER
Learning To See But Forgetting To Follow: Visual Instruction Tuning Makes LLMs More Prone To Jailbreak Attacks
As of 18 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 5 inbound Pith citation observations for arXiv:2405.04403.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-15T14:24:49.653520Z
A source-named dated measurement, never combined with another source.
Source: pith, observed 2026-08-07T19:45:21.791386Z
Reference resolution
0 of 0 outbound references displayed
- verified exact0
- verified fuzzy0
- unresolved0
- parse uncertain0
- malformed identifier0
- metadata mismatch0
External citation measurements
No source-named external measurement is stored.
Outbound references
No outbound reference observations are available for this paper version.
Pith citing papers
Observation f12e9d07-da67-49af-9d46-e5fc31267973 · inbound
Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness cites this paper.
Double Visual Defense: Adversarial Pre-training and Instruction Tuning for Improving Vision-Language Model Robustness Learning To See But Forgetting To Follow: Visual Instruction Tuning Makes LLMs More Prone To Jailbreak Attacks
Reference 34
- Resolution
- unresolved
- no resolver link, observed 2026-08-10T20:06:24.601160Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d7d16bc6-919d-4354-ae2b-346450b22a2b · inbound
A Survey of Safety on Large Vision-Language Models: Attacks, Defenses and Evaluations cites this paper.
A Survey of Safety on Large Vision-Language Models: Attacks, Defenses and Evaluations Learning To See But Forgetting To Follow: Visual Instruction Tuning Makes LLMs More Prone To Jailbreak Attacks
Reference 73
- Resolution
- verified exact
- local_arxiv, observed 2026-08-07T19:45:21.797042Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation dadd5531-ff1d-44e6-aedc-3ccc2cf2827b · inbound
VERA-V: Variational Inference Framework for Jailbreaking Vision-Language Models cites this paper.
VERA-V: Variational Inference Framework for Jailbreaking Vision-Language Models Learning To See But Forgetting To Follow: Visual Instruction Tuning Makes LLMs More Prone To Jailbreak Attacks
Reference 22
- Resolution
- unresolved
- no resolver link, observed 2026-08-04T09:02:39.371506Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 34595cda-3422-43bf-b86c-5a7e86519096 · inbound
$PC^2$: Politically Controversial Content Generation via Jailbreaking Attacks on GPT-based Text-to-Image Models cites this paper.
$PC^2$: Politically Controversial Content Generation via Jailbreaking Attacks on GPT-based Text-to-Image Models Learning To See But Forgetting To Follow: Visual Instruction Tuning Makes LLMs More Prone To Jailbreak Attacks
Reference 25
- Resolution
- unresolved
- no resolver link, observed 2026-08-03T11:47:41.539959Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 490d3cb1-abf5-456a-8af5-94c4a05e0634 · inbound
SafeCap: Improving LVLM Safety with Image Captioning Reinforcement Learning cites this paper.
SafeCap: Improving LVLM Safety with Image Captioning Reinforcement Learning Learning To See But Forgetting To Follow: Visual Instruction Tuning Makes LLMs More Prone To Jailbreak Attacks
Reference 73
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T14:24:49.653520Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.