Paper Citation Record · LEDGER

RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models

As of 19 August 2026, this Paper Citation Record lists 31 of 31 outbound references and 6 inbound Pith citation observations for arXiv:2504.18041.

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

pith.paper-citation-record.v1
2504.18041 v1

Coverage vector

measured 31 of 31 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-16T10:29:57.550353Z

measured 37 of 37 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+00:00

measured 6 of 6 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T15:41:04.875614Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-18T09:31:11.593419Z

Reference resolution

31 of 31 outbound references displayed

verified exact0
verified fuzzy9
unresolved22
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 2c1893c2-3a6e-4583-9fd4-623b3e227a13 · outbound

This paper cites an unresolved cited work.

RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models Unresolved cited work

Reference 1

Resolution: unresolved; raw_fallback, observed 2026-08-16T10:29:58.037940Z

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 60fa8cb3-811a-40ba-9dbf-f0f858f60a8a · outbound

This paper cites Is My Data in Your Retrieval Database? Membership Inference Attacks Against Retrieval Augmented Generation.

RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models Is My Data in Your Retrieval Database? Membership Inference Attacks Against Retrieval Augmented Generation

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-16T10:29:57.404378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07af6f64-a84a-4a1e-b80c-7ccce68d9275 · outbound

This paper cites 3https://solr.apache.org/ Figure 10: Risk taxonomy and the distribution in the dataset.

RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models 3https://solr.apache.org/ Figure 10: Risk taxonomy and the distribution in the dataset

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:29:58.007143Z

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 b122dc55-bd93-46d8-b38f-0d78d2e52aa9 · outbound

This paper cites Alternative Strategies.

RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models **Alternative Strategies**

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:29:57.861640Z

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 dff29cc4-f398-4a12-bb8c-6a1dc72f28bb · outbound

This paper cites COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability.

RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-16T10:29:57.422108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20ede321-667e-4ae5-9b19-192c6195c0c0 · outbound

This paper cites Challenges and Applications of Large Language Models.

RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models Challenges and Applications of Large Language Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-16T10:29:57.427234Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 232bd439-1663-492d-ad5f-2cef933f4062 · outbound

This paper cites Against The Achilles' Heel: A Survey on Red Teaming for Generative Models.

RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models Against The Achilles' Heel: A Survey on Red Teaming for Generative Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-16T10:29:57.432423Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5f1baa3-fe14-4328-a96f-1bc2327d9050 · outbound

This paper cites AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs.

RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-16T10:29:57.437591Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f699d7e3-e447-4d0b-9977-6682cba48ecc · outbound

This paper cites Code Llama: Open Foundation Models for Code.

RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models Code Llama: Open Foundation Models for Code

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-16T10:29:57.443111Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf98d4d6-5101-4364-8696-95ff4bf2126d · outbound

This paper cites Machine Against the RAG: Jamming Retrieval-Augmented Generation with Blocker Documents.

RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models Machine Against the RAG: Jamming Retrieval-Augmented Generation with Blocker Documents

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-16T10:29:57.447803Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aeed093f-f5ba-4031-bbf2-4c746750cc0d · outbound

This paper cites Zephyr: Direct Distillation of LM Alignment.

RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models Zephyr: Direct Distillation of LM Alignment

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-16T10:29:57.453017Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 671412c8-c8ae-4062-9ab7-143bd839b3d3 · outbound

This paper cites BloombergGPT: A Large Language Model for Finance.

RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models BloombergGPT: A Large Language Model for Finance

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-16T10:29:57.458833Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64f99e1e-a85a-42e2-8030-0e496e3cc9aa · outbound

This paper cites an unresolved cited work.

RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models Unresolved cited work

Reference 14

Resolution: unresolved; raw_fallback, observed 2026-08-16T10:29:58.022714Z

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 49959e20-0394-42ef-9249-5a3c5613c84b · outbound

This paper cites Answer the following question.

RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models Answer the following question

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:29:57.992349Z

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 7e5fd2be-93fe-41ac-b6c8-ea90272f8ee5 · outbound

This paper cites Answer the following question.

RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models Answer the following question

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:29:57.977500Z

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 79acb5b9-ae47-4b22-a402-5d7449c08c71 · outbound

This paper cites Yes" or.

RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models Yes" or

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:29:57.963473Z

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 560eb931-8a9d-4604-bed0-9d9d554e4c0a · outbound

This paper cites an unresolved cited work.

RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models Unresolved cited work

Reference 19

Resolution: unresolved; raw_fallback, observed 2026-08-16T10:29:57.949387Z

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 abb9c132-c671-4133-9bdb-88f960657034 · outbound

This paper cites an unresolved cited work.

RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models Unresolved cited work

Reference 20

Resolution: unresolved; raw_fallback, observed 2026-08-16T10:29:57.935101Z

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 15332046-8024-4733-b47e-f1c6b21a31a2 · outbound

This paper cites During the Chase.

RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models **During the Chase**

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:29:57.920618Z

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 a78a266e-8561-489e-abdf-1e6be1af22f3 · outbound

This paper cites an unresolved cited work.

RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models Unresolved cited work

Reference 22

Resolution: unresolved; raw_fallback, observed 2026-08-16T10:29:57.906426Z

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 3ac543b6-3eb6-428b-828b-a8bea10b09c7 · outbound

This paper cites an unresolved cited work.

RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models Unresolved cited work

Reference 23

Resolution: unresolved; raw_fallback, observed 2026-08-16T10:29:57.891806Z

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 0cf5dd5f-f7d1-4992-a5a8-3c99d50f4a6a · outbound

This paper cites an unresolved cited work.

RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models Unresolved cited work

Reference 24

Resolution: unresolved; raw_fallback, observed 2026-08-16T10:29:57.876899Z

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 f58367e2-b4d9-463b-973b-7f464bfdbe53 · outbound

This paper cites an unresolved cited work.

RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models Unresolved cited work

Reference 26

Resolution: unresolved; raw_fallback, observed 2026-08-16T10:29:57.846019Z

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 6977f61e-fb01-4c23-937e-2cb83d7fe06c · outbound

This paper cites an unresolved cited work.

RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models Unresolved cited work

Reference 27

Resolution: unresolved; raw_fallback, observed 2026-08-16T10:29:57.829745Z

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 a21c6dce-1b91-40ff-976c-9c331001af02 · outbound

This paper cites Post-Chase.

RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models **Post-Chase**

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:29:57.813229Z

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 76aab10c-e702-4f9a-8b50-83e5a425423c · outbound

This paper cites an unresolved cited work.

RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models Unresolved cited work

Reference 29

Resolution: unresolved; raw_fallback, observed 2026-08-16T10:29:57.798424Z

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 4b1e8a76-b660-405a-a701-e59346151b33 · outbound

This paper cites an unresolved cited work.

RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models Unresolved cited work

Reference 30

Resolution: unresolved; raw_fallback, observed 2026-08-16T10:29:57.782978Z

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 e6e0d140-8097-4f12-9ea7-77ff3da32398 · outbound

This paper cites the news media make global warming appear worse than it really is.

RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models the news media make global warming appear worse than it really is

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:29:57.767132Z

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 cc8b7159-8e69-44ce-b557-a33bbf1808e0 · outbound

This paper cites Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback.

RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-16T10:29:57.410245Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 766b0098-958e-4bac-abff-21c7d008df5c · outbound

This paper cites Jailbreaking Black Box Large Language Models in Twenty Queries.

RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models Jailbreaking Black Box Large Language Models in Twenty Queries

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-16T10:29:57.416147Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7abade08-8214-45e9-92e4-3dcad8e869a6 · outbound

This paper cites In First Conference on Language Modeling.

RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models In First Conference on Language Modeling

Reference 2024

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T10:29:58.051957Z

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.

Pith citing papers

Observation bed10a0c-0df9-4124-9c5c-73aecea8439d · inbound

Safety Degradation in AI Agents cites this paper.

Safety Degradation in AI Agents RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T15:41:04.875614Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bbb68cd4-3423-4fb7-946d-878e2646fb5f · inbound

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval cites this paper.

Scalable Defense against In-the-wild Jailbreaking Attacks with Safety Context Retrieval RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T15:15:48.529201Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c130e7d-4e28-4fdb-aef5-e2eba30ace8f · inbound

Foundation Model Driven Robotics: A Comprehensive Review cites this paper.

Foundation Model Driven Robotics: A Comprehensive Review RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models

Reference 165

Resolution: unresolved; no resolver link, observed 2026-08-06T17:43:53.437109Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f36855d8-2b05-43ce-a2d3-fd1595b7f5c0 · inbound

When Search Goes Wrong: Red-Teaming Web-Augmented Large Language Models cites this paper.

When Search Goes Wrong: Red-Teaming Web-Augmented Large Language Models RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-18T09:31:11.595671Z

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 8e8600dd-0e3f-4d53-88b5-dc422d3f952d · inbound

The Cost of Context: Mitigating Textual Bias in Multimodal Retrieval-Augmented Generation cites this paper.

The Cost of Context: Mitigating Textual Bias in Multimodal Retrieval-Augmented Generation RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-11T19:41:08.787667Z

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 acd50243-8b84-43c3-a8a2-28a2408ee2c6 · inbound

Risky Business: Measuring The Faithfulness-Safety Tension cites this paper.

Risky Business: Measuring The Faithfulness-Safety Tension RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-05T13:40:59.135576Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.