Paper Citation Record · LEDGER

Uncovering Safety Risks of Large Language Models through Concept Activation Vector

As of 20 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 11 inbound Pith citation observations for arXiv:2404.12038.

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

pith.paper-citation-record.v1
2404.12038 v5

Coverage vector

measured 0 of 0 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links

measured 11 of 11 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 2026-08-10T23:40:19.159525Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-11T10:21:04.586767Z

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 f19be64b-8843-4b29-ba7e-9406e9aa6b96 · inbound

On the Validity of Traditional Vulnerability Scoring Systems for Adversarial Attacks against LLMs cites this paper.

On the Validity of Traditional Vulnerability Scoring Systems for Adversarial Attacks against LLMs Uncovering Safety Risks of Large Language Models through Concept Activation Vector

Reference 149

Resolution: unresolved; no resolver link, observed 2026-08-10T23:40:19.159525Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c14d0ef-7e00-433e-b8f6-874c769a2d98 · inbound

Latent-space adversarial training with post-aware calibration for defending large language models against jailbreak attacks cites this paper.

Latent-space adversarial training with post-aware calibration for defending large language models against jailbreak attacks Uncovering Safety Risks of Large Language Models through Concept Activation Vector

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-10T19:08:01.749591Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36981ff1-9520-433a-ad4b-23e1a8cb120f · inbound

Vulnerability Mitigation for Safety-Aligned Language Models via Debiasing cites this paper.

Vulnerability Mitigation for Safety-Aligned Language Models via Debiasing Uncovering Safety Risks of Large Language Models through Concept Activation Vector

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-09T13:14:34.129562Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37a16043-58e6-419d-91b0-a47e917f4c88 · inbound

JBShield: Defending Large Language Models from Jailbreak Attacks through Activated Concept Analysis and Manipulation cites this paper.

JBShield: Defending Large Language Models from Jailbreak Attacks through Activated Concept Analysis and Manipulation Uncovering Safety Risks of Large Language Models through Concept Activation Vector

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-08T12:25:30.692632Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5864e4db-8df3-4dce-830e-4957a71edba1 · inbound

Aligned but Blind: Alignment Increases Implicit Bias by Reducing Awareness of Race cites this paper.

Aligned but Blind: Alignment Increases Implicit Bias by Reducing Awareness of Race Uncovering Safety Risks of Large Language Models through Concept Activation Vector

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-07T12:13:19.638500Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 258cad88-9095-469b-af29-54299a4bf63a · inbound

Internal Value Alignment in Large Language Models through Controlled Value Vector Activation cites this paper.

Internal Value Alignment in Large Language Models through Controlled Value Vector Activation Uncovering Safety Risks of Large Language Models through Concept Activation Vector

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-06T17:17:31.819851Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 50128bf5-2104-432c-8ff7-0d38647da5fd · inbound

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation cites this paper.

Layer-Wise Perturbations via Sparse Autoencoders for Adversarial Text Generation Uncovering Safety Risks of Large Language Models through Concept Activation Vector

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-05T20:31:37.875871Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b24c292-b1f9-4fc1-bc01-f5896cb04529 · inbound

Forewarned is Forearmed: Pre-Synthesizing Jailbreak-like Instructions to Enhance LLM Safety Guardrail to Potential Attacks cites this paper.

Forewarned is Forearmed: Pre-Synthesizing Jailbreak-like Instructions to Enhance LLM Safety Guardrail to Potential Attacks Uncovering Safety Risks of Large Language Models through Concept Activation Vector

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-05T15:19:28.783558Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 602cc282-fca1-45b4-9984-6468cb4cea3a · inbound

Probing the Difficulty Perception Mechanism of Large Language Models cites this paper.

Probing the Difficulty Perception Mechanism of Large Language Models Uncovering Safety Risks of Large Language Models through Concept Activation Vector

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-04T11:17:49.355098Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d42f3c5-fb71-41d3-a016-e7e41c7e5c61 · inbound

The SuperActivator Mechanism: Transformers Concentrate Reliable Concept Signals in the Tail cites this paper.

The SuperActivator Mechanism: Transformers Concentrate Reliable Concept Signals in the Tail Uncovering Safety Risks of Large Language Models through Concept Activation Vector

Reference 83

Resolution: unresolved; no resolver link, observed 2026-08-03T18:33:09.239553Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7161955-188a-4d9c-80d1-901d1077197c · inbound

Why Do Large Language Models Generate Harmful Content? cites this paper.

Why Do Large Language Models Generate Harmful Content? Uncovering Safety Risks of Large Language Models through Concept Activation Vector

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-05-11T10:21:04.601411Z

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.