Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-07T14:10:30.637151Z
Paper Citation Record · LEDGER
As of 9 August 2026, this Paper Citation Record lists 48 of 48 outbound references and 9 inbound Pith citation observations for arXiv:2505.19864.
A citation records a reference. It does not transfer a finding from one paper to another.
Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-07T14:10:30.637151Z
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-06T00:08:57.754979Z
A source-named dated measurement, never combined with another source.
Source: arxiv_reference, observed 2026-07-03T21:28:59.129123Z
48 of 48 outbound references displayed
External citation measurements
No source-named external measurement is stored.
Observation 29521612-a2c8-4f36-86c9-6d1e6c27f3cf · outbound
CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models GPT-4 Technical Report
Reference 1
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 85a8e50d-fb41-4f0f-b282-3d759f7993cd · outbound
CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models Applying generative ai with retrieval augmented generation to summarize and extract key clinical information from electronic health records
Reference 2
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 032a1b81-f937-44b1-aa7a-a4b6d79b5374 · outbound
CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models MS MARCO: A Human Generated MAchine Reading COmprehension Dataset
Reference 3
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation df71ab86-883a-4aa7-8686-fad8041ef2b3 · outbound
CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models InternLM2 Technical Report
Reference 4
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6d1ee5b0-75fb-40ca-b4ef-35fbff9a52ca · outbound
CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models Phantom: General trigger attacks on retrieval augmented language generation.arXiv preprint arXiv:2405.20485, 2024
Reference 5
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ab3a3ce9-8b71-49fc-aec2-a5b61fcce89b · outbound
CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models Benchmarking large language models in retrieval- augmented generation
Reference 6
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 0a3bb760-3cb9-432a-9ea4-d93f89a3f9ae · outbound
CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality.See https://vicuna
Reference 7
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 9b305ce9-8835-4542-8c02-f70e6c6177af · outbound
CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models Typos that Broke the RAG's Back: Genetic Attack on RAG Pipeline by Simulating Documents in the Wild via Low-level Perturbations
Reference 8
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 532fbbfc-6b8d-4268-b013-e94504ae2087 · outbound
CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models The rag paradox: A black-box attack exploiting unintentional vulnerabilities in retrieval-augmented generation systems.arXiv preprint arXiv:2502.20995, 2025
Reference 9
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2dac1c8f-f054-44c6-ba6f-e87e72dcbaf4 · outbound
CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models HotFlip: White-Box Adversarial Examples for Text Classification
Reference 10
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 768efb1d-d160-40ac-aa7a-5be0bd074f82 · outbound
CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models From Local to Global: A Graph RAG Approach to Query-Focused Summarization
Reference 11
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 702308f4-eb02-477b-bec3-7faca8ffa6ad · outbound
CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models A survey on rag meeting llms: Towards retrieval-augmented large language models
Reference 12
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 004ed97d-6616-407c-8cbb-5ee2b0698719 · outbound
CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models CLERC: A Dataset for Legal Case Retrieval and Retrieval-Augmented Analysis Generation
Reference 13
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e0e7690b-a9f4-454e-841e-36d553516da0 · outbound
CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models Unsupervised Dense Information Retrieval with Contrastive Learning
Reference 14
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e8ceed11-e8fc-45db-a13e-a8009bafb673 · outbound
CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models Dense passage retrieval for open-domain question answering
Reference 15
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 87513cf4-d18d-415c-93df-e93facd85e25 · outbound
CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models Natural questions: a benchmark for question answering research.Transactions of the Association for Computational Linguistics, 2019
Reference 16
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 9b53bd99-0c94-42ea-a13d-35e803e95247 · outbound
CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models Retrieval-augmented generation for knowledge- intensive nlp tasks.Advances in neural information processing systems, 33, 2020
Reference 17
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation bcdae5e4-f9b9-46d0-8d03-89568c641d88 · outbound
CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models DeepSeek-V3 Technical Report
Reference 18
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 15517f4f-d838-4b4e-9a5c-7398c98f1332 · outbound
CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models Backdoor Attacks on Dense Retrieval via Public and Unintentional Triggers
Reference 19
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 25d1c000-8ccf-4ffe-8c2c-852aa35531f9 · outbound
CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models Crud-rag: A comprehensive chinese benchmark for retrieval-augmented generation of large language models.ACM Transactions on Information Systems, 43(2), 2025
Reference 20
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation fb1f9b12-2909-4a86-987c-bd2ecccace17 · outbound
CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models Training language models to follow instructions with human feedback.Advances in neural information processing systems, 2022
Reference 21
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ada1333a-fc42-4d91-8b3a-e65768243590 · outbound
CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models LegalBench-RAG: A Benchmark for Retrieval-Augmented Generation in the Legal Domain
Reference 22
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5df4df5c-7f6d-48f2-948b-9ad3def21432 · outbound
CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models Evaluating retrieval quality in retrieval-augmented generation
Reference 23
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 53d8fe85-cbbf-4e45-a7b3-dc0cce0db2e9 · outbound
CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models Ctrlrag: Black-box adversarial attacks based on masked language models in retrieval-augmented language generation.arXiv preprint arXiv:2503.06950, 2025
Reference 24
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation adfb90fa-39af-4f16-8a66-8e977be92ee6 · outbound
CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models
Reference 25
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e5095846-3b33-44bb-9870-5a38cdb5c500 · outbound
CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models Llama 2: Open Foundation and Fine-Tuned Chat Models
Reference 26
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9d277370-7de5-4f43-b1eb-128abb4f7765 · outbound
CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models Potential for gpt technology to optimize future clinical decision-making using retrieval-augmented generation.Annals of biomedical engineering, 2024
Reference 27
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 91f831da-72b3-4144-9b5e-268a50d7cba1 · outbound
CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models Cbr-rag: case-based reasoning for retrieval augmented generation in llms for legal question answering
Reference 28
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 9b205070-5805-495f-9ce7-2dfd05221a80 · outbound
CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models Benchmarking retrieval-augmented generation for medicine
Reference 29
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 7415313f-79aa-4b89-ba19-dc78a236c6ee · outbound
CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval
Reference 30
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ad3665db-4331-49e8-bf14-e2d05e012165 · outbound
CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models An LLM can Fool Itself: A Prompt-Based Adversarial Attack
Reference 31
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 22c15008-96fb-4937-b186-37067ed30236 · outbound
CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models An llm- assisted easy-to-trigger backdoor attack on code completion models: Injecting disguised vulnerabilities against strong detection
Reference 32
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 7b037daa-0382-4422-8762-10b1b22939dd · outbound
CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models Qwen2.5 Technical Report
Reference 33
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6e7232a5-4fd9-474a-b980-8fe9068fa0f2 · outbound
CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering
Reference 34
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 4796b999-d99e-4a4a-9fd8-3a63dacb6d6d · outbound
CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models Financial Report Chunking for Effective Retrieval Augmented Generation
Reference 35
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9bbcce3a-27e3-4172-9929-b9fcc807415a · outbound
CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models Enhancing financial sentiment analysis via retrieval augmented large language models
Reference 36
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 89f98b10-11ea-4407-bae3-161604192baf · outbound
CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models Medrag: Enhancing retrieval-augmented generation with knowledge graph-elicited reasoning for healthcare copilot
Reference 37
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation a79808e6-d544-4845-973a-4c97cd020dc1 · outbound
CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models Optimizing llm based retrieval augmented generation pipelines in the financial domain
Reference 38
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation ab2d30a3-cda8-4b78-9131-51617e5d1c12 · outbound
CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models Poisoning Retrieval Corpora by Injecting Adversarial Passages
Reference 39
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation cd607889-5dbe-41a1-ba0e-c8372564d09e · outbound
CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models Universal and Transferable Adversarial Attacks on Aligned Language Models
Reference 40
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6df26f02-16ec-4f8e-a0a7-c0d203ce0b6e · outbound
CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models [Q]”. Here is the desired answer: “[R]
Reference 41
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 2139def9-d5f2-4739-b5f9-235c11bbf872 · outbound
CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models Unresolved cited work
Reference 42
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation ad308c7e-00aa-4ca7-b6ae-ce6f26788455 · outbound
CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models Unresolved cited work
Reference 43
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 346cfee5-5e96-4d23-9dfa-5776e1001426 · outbound
CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models I don’t know
Reference 44
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation ec988d04-1ca4-452f-a169-a840382b275b · outbound
CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models •Comprehensive ASR (CASR): A weighted average of ASR across top-kvalues: CASR= Pn k=1 k·ASR kPn k=1 k
Reference 45
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation af8b713c-ccba-4f5c-bd9a-8cbac8d8e05c · outbound
CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models F1 = 2·Precision·Recall Precision+Recall 16 •Toxicity Efficiency Score (TES): Captures the ratio of attack success to retrievability: T ES= ASR F1
Reference 46
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 347263ff-15c1-45c7-a9ff-52857e369093 · outbound
CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models When asked... please output
Reference 47
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation c846deed-ddf9-418f-a299-b6869c4e2fb0 · outbound
CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models To Make You Feel My Love
Reference 48
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 7d88d0b4-fc0c-4592-b4ff-567e1d06b3e0 · inbound
UniC-RAG: Universal Knowledge Corruption Attacks to Retrieval-Augmented Generation CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models
Reference 24
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8012415b-f996-43d8-b7ca-2841402e00a8 · inbound
Atomic clocks and gravitational waves as probes of non-metricity CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models
Reference 98
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation be974dc6-7a58-41bd-9f37-d4e1824463a7 · inbound
RAGShield: Detecting Numerical Claim Manipulation in Government RAG Systems CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models
Reference 8
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation fcaad7e1-fa84-44b2-b102-80911461e43c · inbound
RefineRAG: Word-Level Poisoning Attacks via Retriever-Guided Text Refinement CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models
Reference 17
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 1fa20cf7-b8ca-4b9e-acc6-7cdba9fc5831 · inbound
CleanBase: Detecting Malicious Documents in RAG Knowledge Databases CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models
Reference 35
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 1aeb5030-59cc-48cb-a729-c3132108daee · inbound
When Poison Fails After Retrieval: Revisiting Corpus Poisoning under Chunking and Reranking Pipelines CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models
Reference 23
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation bc29ac4a-de12-4e3f-96a1-196ea7bf1b97 · inbound
Conflict-Aware Retriever Editing for Knowledge Injection Attacks on LLM-Based RAG Systems CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models
Reference 33
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.
Observation 827af0f7-c975-4788-9ad7-0d6af76750d3 · inbound
Large Language Models in Misinformation Ecosystems: Misuse, Defense, and Vulnerability CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models
Reference 95
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 5a9fb543-f8cf-43f2-86eb-ce9ae019f9d5 · inbound
DenialRAG: Single-Document RAG Poisoning via Embedded Parametric Denial CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models
Reference 16
Source-reported events for the cited work
Unavailable: canonical work link unavailable.