Paper Citation Record · LEDGER

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version)

As of 7 August 2026, this Paper Citation Record lists 86 of 86 outbound references and 3 inbound Pith citation observations for arXiv:2508.20083.

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

pith.paper-citation-record.v1
2508.20083 v2

Coverage vector

measured 86 of 86 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-05T15:18:37.195476Z

measured 89 of 89 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-03T05:31:33.371931Z

measured 1 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

86 of 86 outbound references displayed

verified exact1
verified fuzzy46
unresolved37
parse uncertain1
malformed identifier1
metadata mismatch0

External citation measurements

0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation 55aa9561-40a5-4b65-aa95-7eb140fecceb · outbound

This paper cites https://www.nvidia.com/en-us/ai-on-rtx/chatrtx/.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) https://www.nvidia.com/en-us/ai-on-rtx/chatrtx/

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:29.066232Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dbf83c86-4d04-46fe-a370-3be10d24e81b · outbound

This paper cites https://www.langchain.com/.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) https://www.langchain.com/

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:29.162119Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db1f7eaa-24a1-47f1-9018-980829d1b382 · outbound

This paper cites https://github.com/0xeb/TheBigPromptLibrary,.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) https://github.com/0xeb/TheBigPromptLibrary,

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:29.256301Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23e7068f-d13f-4bfe-a959-dd31db0d9ef7 · outbound

This paper cites https://github.com/danielrosehill/ System-Prompt-Library, 2023.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) https://github.com/danielrosehill/ System-Prompt-Library, 2023

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:29.462948Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58bb89ef-1f52-423f-915d-0fd233120b03 · outbound

This paper cites Detecting Language Model Attacks with Perplexity.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Detecting Language Model Attacks with Perplexity

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:29.558593Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a2728b2-269c-479b-a2f2-954db4432f80 · outbound

This paper cites Gasliteing the retrieval: Explor- ing vulnerabilities in dense embedding-based search.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Gasliteing the retrieval: Explor- ing vulnerabilities in dense embedding-based search

Reference 6

Resolution: verified exact; raw_fallback, observed 2026-08-05T15:18:38.189861Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6b07b563-0bdf-4f81-b41d-24202a7c815c · outbound

This paper cites Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:29.760311Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0432415-65b2-4fe6-8bd5-60beead500a0 · outbound

This paper cites Poisoning and Backdooring Contrastive Learning.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Poisoning and Backdooring Contrastive Learning

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:29.850429Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03ab3a91-bfda-4ac4-9441-6aaa8d98c155 · outbound

This paper cites Towards evaluating the robustness of neural networks.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Towards evaluating the robustness of neural networks

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:29.951628Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e94e4b5-fd30-4299-b43e-46657abb0bc3 · outbound

This paper cites LexGLUE: A benchmark dataset for legal language understanding in English.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) LexGLUE: A benchmark dataset for legal language understanding in English

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:47.472541Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation c7e67935-f9b6-4882-8965-81aa5a82b4f7 · outbound

This paper cites FinQA: A dataset of numerical reasoning over financial data.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) FinQA: A dataset of numerical reasoning over financial data

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:47.321879Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9e5ede33-c7bd-4a5f-9c59-f6f524bd36f7 · outbound

This paper cites Trojanrag: Retrieval-augmented generation can be backdoor driver in large language models, 2024.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Trojanrag: Retrieval-augmented generation can be backdoor driver in large language models, 2024

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:47.137367Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f60cf567-269b-484b-88ef-6ac38018f281 · outbound

This paper cites Debiased contrastive learning.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Debiased contrastive learning

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:46.941144Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 22dcd998-8267-4973-9c6e-4d124faa0e1a · outbound

This paper cites Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning, 2025.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning, 2025

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:30.624100Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b27447e8-3b68-44c6-887c-a94726b7c1b9 · outbound

This paper cites Deepseek-v3 technical report, 2025.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Deepseek-v3 technical report, 2025

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:30.755713Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d2ab33f-4c48-477a-9960-3ead9c63aa23 · outbound

This paper cites The philosopher’s stone: Trojaning plugins of large language models.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) The philosopher’s stone: Trojaning plugins of large language models

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:46.765994Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 820052b5-cb92-4ae1-a444-79a591bb7b21 · outbound

This paper cites Synthetic disinformation attacks on automated fact verification systems.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Synthetic disinformation attacks on automated fact verification systems

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:46.584153Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5efdf519-e22b-494d-a8d7-4525df41178e · outbound

This paper cites Hot- Flip: White-box adversarial examples for text classification.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Hot- Flip: White-box adversarial examples for text classification

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:46.382053Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 29bd5bac-4228-4a6e-aa14-c21894a1b4b0 · outbound

This paper cites Defending against knowledge poisoning attacks during retrieval-augmented generation.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Defending against knowledge poisoning attacks during retrieval-augmented generation

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:31.227679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3788abba-d1c1-47c5-ae61-8e6e5b59eb7a · outbound

This paper cites Hugging face: Open-source ai community.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Hugging face: Open-source ai community

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:46.255861Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e6e4c22f-6fcb-4a2d-b31b-6abcaf20cb44 · outbound

This paper cites Demystifying Prompts in Language Models via Perplexity Estimation.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Demystifying Prompts in Language Models via Perplexity Estimation

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:31.533223Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9e8dfa07-756b-4741-b17a-a1f803c01888 · outbound

This paper cites Not what you’ve signed up for: Com- promising real-world llm-integrated applications with indirect prompt injection.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Not what you’ve signed up for: Com- promising real-world llm-integrated applications with indirect prompt injection

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:46.111441Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ef52d9f2-e44b-466b-b6cf-1572c8c57dc4 · outbound

This paper cites Retrieval augmented language model pre-training.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Retrieval augmented language model pre-training

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:45.922497Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e70a30d2-5fcc-45f7-b92b-8a3cbac85ef2 · outbound

This paper cites Aging with grace: Lifelong model editing with discrete key-value adaptors.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Aging with grace: Lifelong model editing with discrete key-value adaptors

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:45.804889Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation fbbc13e1-7cd2-4b10-8d91-3d034e208141 · outbound

This paper cites A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions.ACM Transactions on Information Systems , 43(2):1–55, 2025.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) A survey on hallucination in large language models: Principles, taxonomy, challenges, and open questions.ACM Transactions on Information Systems , 43(2):1–55, 2025

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:45.669656Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 2682d8af-3638-4532-b4a2-50705da6d7d0 · outbound

This paper cites Qwen2.5-Coder Technical Report.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Qwen2.5-Coder Technical Report

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:32.147743Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0226bb2c-5973-4e92-b4b5-6c0eca2af22d · outbound

This paper cites Unsupervised dense information retrieval with contrastive learning.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Unsupervised dense information retrieval with contrastive learning

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:45.527583Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 12c51656-ef2a-41d9-bd34-fce550565746 · outbound

This paper cites Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:32.316307Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49b1555e-ccf0-476f-8907-1d048457b1b4 · outbound

This paper cites Atlas: Few-shot learning with retrieval augmented language models.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Atlas: Few-shot learning with retrieval augmented language models

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:45.337037Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 25fffe44-6e47-4c59-b5fa-d35df3341589 · outbound

This paper cites Baseline Defenses for Adversarial Attacks Against Aligned Language Models.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Baseline Defenses for Adversarial Attacks Against Aligned Language Models

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:32.592658Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6e69cf5-5f39-41b9-b2fc-f24dd853c922 · outbound

This paper cites Interpolated estimation of markov source parameters from sparse data.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Interpolated estimation of markov source parameters from sparse data

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:45.147882Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation bac2da26-d497-4ef8-9a50-28cb0382ff34 · outbound

This paper cites A Survey on Large Language Models for Code Generation.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) A Survey on Large Language Models for Code Generation

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:32.857911Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 914b416e-d7e7-40c9-b8f1-54a6eb0e3246 · outbound

This paper cites Evaluating LLMs at Detecting Errors in LLM Responses.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Evaluating LLMs at Detecting Errors in LLM Responses

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:32.971133Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3cba4a2-152e-490a-8c38-ba223eb65976 · outbound

This paper cites Super- vised contrastive learning.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Super- vised contrastive learning

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:44.980564Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6ade8882-c79a-456d-9110-0fe0122b8fe8 · outbound

This paper cites Large language models are zero-shot reasoners.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Large language models are zero-shot reasoners

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:44.794318Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 830d0e25-51dc-4106-97b4-046a06e6db59 · outbound

This paper cites Natural questions: a benchmark for question answering research.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Natural questions: a benchmark for question answering research

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:33.241369Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89d5db61-e3ba-4ce3-bf6d-1bcbaf85f44f · outbound

This paper cites Retrieval-augmented generation for knowledge- intensive nlp tasks.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Retrieval-augmented generation for knowledge- intensive nlp tasks

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:44.645112Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 802859f6-32b5-4a9a-9d0a-c8a9d2d5f946 · outbound

This paper cites Solving quantitative reasoning problems with language models.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Solving quantitative reasoning problems with language models

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:44.489971Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f24e23c1-1dc6-46a7-b4cb-e7a745b3411b · outbound

This paper cites Superfiltering: Weak-to-strong data filtering for fast instruction-tuning.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Superfiltering: Weak-to-strong data filtering for fast instruction-tuning

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:44.316321Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 824e0d85-b6f1-4ab4-bc31-2f47d459d15b · outbound

This paper cites Pmet: precise model editing in a transformer.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Pmet: precise model editing in a transformer

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:44.178913Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 6757cd66-de00-4152-a8e4-d029d4aaf072 · outbound

This paper cites Graphrag under fire, 2025.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Graphrag under fire, 2025

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:33.648148Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e5ca3fa-e3fb-4aa1-854a-1227d4cd057a · outbound

This paper cites an unresolved cited work.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Unresolved cited work

Reference 42

Resolution: unresolved; raw_fallback, observed 2026-08-05T15:18:44.028379Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 42aafb07-dbaa-4875-8c20-b4fc6ea3e4ca · outbound

This paper cites Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:43.726984Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4435b83d-ec90-449c-9044-ac49e45ebe75 · outbound

This paper cites Prompt Injection attack against LLM-integrated Applications.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Prompt Injection attack against LLM-integrated Applications

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:33.976569Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5aea91cf-0960-4c00-aef4-e7167af259a0 · outbound

This paper cites Formalizing and benchmarking prompt injection attacks and defenses.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Formalizing and benchmarking prompt injection attacks and defenses

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:43.517783Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation c172727a-ea97-4871-b8e8-160cba06aedb · outbound

This paper cites fixed thinking pattern.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) fixed thinking pattern

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:43.395205Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9ab6a138-197b-4240-99a0-d9c257a07106 · outbound

This paper cites Explicit eigenvalue regularization improves sharpness-aware minimization.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Explicit eigenvalue regularization improves sharpness-aware minimization

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:43.278822Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 8accfeac-5dbc-4308-b2f6-e09dc0fa53ac · outbound

This paper cites Repackage-proofing android apps.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Repackage-proofing android apps

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:43.066422Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation adb0b244-37e3-47f7-a17c-0c06d3f3cf88 · outbound

This paper cites Self-refine: Iterative refinement with self-feedback.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Self-refine: Iterative refinement with self-feedback

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:34.265027Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b57ad28-d1a8-4428-8745-344912be042c · outbound

This paper cites Locating and Editing Factual Associations in GPT.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Locating and Editing Factual Associations in GPT

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:34.318320Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7da12cbd-4511-4542-9c0b-edba40e5333e · outbound

This paper cites Mass editing memory in a transformer.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Mass editing memory in a transformer

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:42.867752Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 8e237f56-a919-4a77-9fd9-0c8047c3bc4a · outbound

This paper cites Fast model editing at scale.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Fast model editing at scale

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:42.716529Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 40916261-de2f-4c64-a6db-3f9db99d061c · outbound

This paper cites Memory-based model editing at scale.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Memory-based model editing at scale

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:42.507125Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9599ab60-1f0c-44f3-8980-3cdb02a26953 · outbound

This paper cites Ms marco: A human-generated machine reading comprehension dataset.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Ms marco: A human-generated machine reading comprehension dataset

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:42.314551Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b2d3b8c0-6b7c-4392-a11a-6818ad90361c · outbound

This paper cites Passage re-ranking with bert, 2020.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Passage re-ranking with bert, 2020

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:42.128099Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 42f775e2-7dfc-4bfe-b1f3-b2bea3f5db04 · outbound

This paper cites Gpt-4 technical report, 2024.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Gpt-4 technical report, 2024

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:34.680906Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 732b14db-889f-4d44-a499-7fbb268b2ee4 · outbound

This paper cites gpt-oss-120b & gpt-oss-20b model card.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) gpt-oss-120b & gpt-oss-20b model card

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:41.932854Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e8bc2aae-fe5d-44f5-973b-62393fbe13f5 · outbound

This paper cites On the Risk of Misinformation Pollution with Large Language Models.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) On the Risk of Misinformation Pollution with Large Language Models

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:34.810186Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5175eb71-0be1-40d9-a066-dbb1718df9a1 · outbound

This paper cites Stress-testing machine generated text detection: Shifting language models writing style to fool detectors.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Stress-testing machine generated text detection: Shifting language models writing style to fool detectors

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:41.723970Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 2842a7e2-f8b8-4076-a160-13c03331046c · outbound

This paper cites Ignore Previous Prompt: Attack Techniques For Language Models.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Ignore Previous Prompt: Attack Techniques For Language Models

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:34.967028Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a81d89ae-6e41-4344-bb67-f46d5c64b49a · outbound

This paper cites RocketQA: An optimized training approach to dense passage retrieval for open-domain question answering.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) RocketQA: An optimized training approach to dense passage retrieval for open-domain question answering

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:41.464130Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 765b4711-a084-4d67-834b-d25f057be2d5 · outbound

This paper cites QwQ: Reflect deeply on the boundaries of the unknown.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) QwQ: Reflect deeply on the boundaries of the unknown

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:41.270279Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 95c4d7d9-ca33-4b6d-8c26-b3b0159e6359 · outbound

This paper cites I2C-Huelva at SemEval-2024 task 8: Boosting AI-generated text detection with multimodal models and optimized ensembles.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) I2C-Huelva at SemEval-2024 task 8: Boosting AI-generated text detection with multimodal models and optimized ensembles

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:41.044401Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d61b9e26-74a7-4bbe-b04e-e4c9ee41c09c · outbound

This paper cites Repack me if you can: An anti-repackaging solution based on android virtualization.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Repack me if you can: An anti-repackaging solution based on android virtualization

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:40.853319Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5dab7ed9-c72b-4268-aa29-e212bb21108b · outbound

This paper cites Poison frogs! targeted clean-label poisoning attacks on neural networks.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Poison frogs! targeted clean-label poisoning attacks on neural networks

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:40.611890Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 75a04176-77f5-4f47-a2d1-e054b51a60a9 · outbound

This paper cites Backdoor scanning for deep neural networks through k-arm optimization.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Backdoor scanning for deep neural networks through k-arm optimization

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:40.314326Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f489c20f-9bec-4208-8f26-875ad47ee95f · outbound

This paper cites Powernorm: Rethinking batch normalization in transformers.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Powernorm: Rethinking batch normalization in transformers

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:40.118124Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation e5fd6334-dd59-4d28-85b8-457cdc28ec20 · outbound

This paper cites Reflexion: Language agents with verbal reinforcement learning.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Reflexion: Language agents with verbal reinforcement learning

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:39.928427Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a2c6c574-d92e-4016-9556-c0989ba512e1 · outbound

This paper cites Large language models encode clinical knowledge.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Large language models encode clinical knowledge

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:35.746903Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba4c075b-2131-449f-b30c-1b2a09e9cd9f · outbound

This paper cites Massive Editing for Large Language Models via Meta Learning.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Massive Editing for Large Language Models via Meta Learning

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:35.887794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19d9b696-644f-43cc-9d82-fe81e3f9a17e · outbound

This paper cites Qwen2.5 Technical Report.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Qwen2.5 Technical Report

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:36.013369Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 235b85ee-0ecd-45ad-8c79-06d2681ab93f · outbound

This paper cites BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:36.083612Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55ebde51-8a31-4995-bd9d-0e261e3832ee · outbound

This paper cites LLMs cannot find reasoning errors, but can correct them given the error location.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) LLMs cannot find reasoning errors, but can correct them given the error location

Reference 73

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:39.714624Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4572fae7-f455-4cfb-af79-53c7ac271978 · outbound

This paper cites Neural cleanse: Identifying and miti- gating backdoor attacks in neural networks.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Neural cleanse: Identifying and miti- gating backdoor attacks in neural networks

Reference 74

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:39.487306Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 4116f134-f0dc-4115-941e-63ece8920079 · outbound

This paper cites Large language models are not fair evaluators.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Large language models are not fair evaluators

Reference 75

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:39.261767Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 3e379488-4064-4492-8cdb-bd1bf5248298 · outbound

This paper cites Self-Consistency Improves Chain of Thought Reasoning in Language Models.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Self-Consistency Improves Chain of Thought Reasoning in Language Models

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:36.456523Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4ba0dc7-f794-42dc-a58d-ba88f479d362 · outbound

This paper cites Rethinking the reverse-engineering of trojan triggers.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Rethinking the reverse-engineering of trojan triggers

Reference 77

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:39.062504Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation fd9d9b56-cc7e-4450-8b44-d1d3de4895fc · outbound

This paper cites Generating sequences by learning to self-correct.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Generating sequences by learning to self-correct

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:36.655168Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70312e76-645c-420a-9331-4bab31908e57 · outbound

This paper cites HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:36.782414Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation babe2dcc-44a2-4ac6-a8c0-28d8ff7e5e05 · outbound

This paper cites Melo: Enhancing model editing with neuron-indexed dynamic lora.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Melo: Enhancing model editing with neuron-indexed dynamic lora

Reference 80

Resolution: verified fuzzy; raw_fallback, observed 2026-08-05T15:18:38.866598Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ad58ddcf-7096-454f-a151-4e085f27729b · outbound

This paper cites Benchmarking Poisoning Attacks against Retrieval-Augmented Generation.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Benchmarking Poisoning Attacks against Retrieval-Augmented Generation

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:36.938530Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fdd741db-c527-4127-8bf4-af3025922256 · outbound

This paper cites an unresolved cited work.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Unresolved cited work

Reference 82

Resolution: unresolved; raw_fallback, observed 2026-08-05T15:18:38.667797Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f2b911c7-cfd5-487d-abc9-14a1fca88c14 · outbound

This paper cites Poisoning Retrieval Corpora by Injecting Adversarial Passages.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Poisoning Retrieval Corpora by Injecting Adversarial Passages

Reference 83

Resolution: unresolved; no resolver link, observed 2026-08-05T15:18:37.129287Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4754624b-1e61-4329-99d3-cfd15157e399 · outbound

This paper cites case_id": 0,.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) case_id": 0,

Reference 84

Resolution: malformed identifier; raw_fallback, observed 2026-08-05T15:18:38.413036Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 27bab412-d921-4c03-83b9-11d8e0b5e38c · outbound

This paper cites an unresolved cited work.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Unresolved cited work

Reference 2022

Resolution: unresolved; raw_fallback, observed 2026-08-05T15:18:43.897534Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 2915ef4d-8d6f-4c45-843c-e4c1052bc8c7 · outbound

This paper cites an unresolved cited work.

DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version) Unresolved cited work

Reference 2023

Resolution: parse uncertain; no resolver link, observed 2026-08-05T15:18:29.375772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 7c65dd72-7402-4cd4-aeb6-55027e13f911 · inbound

CAM: A Causality-based Analysis Framework for Multi-Agent Code Generation Systems cites this paper.

CAM: A Causality-based Analysis Framework for Multi-Agent Code Generation Systems DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version)

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-03T05:31:33.371931Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f587150e-d17b-4a46-af15-2eaa6d5cefd5 · inbound

Influence Factors on RAG Poisoning cites this paper.

Influence Factors on RAG Poisoning DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version)

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-07-21T01:20:36.348935Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 165eb885-42c6-494c-bef0-b2c4a8008985 · inbound

Influence Factors on RAG Poisoning cites this paper.

Influence Factors on RAG Poisoning DisarmRAG: Stealthy Retriever-Centric Poisoning to Disable Self-Correction in Retrieval-Augmented Generation (Extended Version)

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-07-21T01:20:36.348935Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.