Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-12T15:00:14.332766Z
Paper Citation Record · LEDGER
As of 13 August 2026, this Paper Citation Record lists 40 of 40 outbound references and 4 inbound Pith citation observations for arXiv:2411.14738.
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 2026-08-12T15:00:14.332766Z
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-12T06:34:41.77262+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-08-11T22:17:42.668642Z
A source-named dated measurement, never combined with another source.
Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z
40 of 40 outbound references displayed
External citation measurements
0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z
Observation ea46f740-3083-412f-babf-c4ac407ec7a5 · outbound
Universal and Context-Independent Triggers for Precise Control of LLM Outputs GPT-4 Technical Report
Reference 1
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ceaf84e8-4f81-4754-aa31-12397168f81b · outbound
Universal and Context-Independent Triggers for Precise Control of LLM Outputs Unresolved cited work
Reference 2
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 93f1d166-17e3-4b23-9cfb-9c3017462153 · outbound
Universal and Context-Independent Triggers for Precise Control of LLM Outputs Jailbreaking Black Box Large Language Models in Twenty Queries
Reference 3
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 8f789eb0-bac2-4151-831c-c9939897a796 · outbound
Universal and Context-Independent Triggers for Precise Control of LLM Outputs The Llama 3 Herd of Models
Reference 4
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ac5ea2b2-afda-4d9a-934e-c1ffc6cc8dee · outbound
Universal and Context-Independent Triggers for Precise Control of LLM Outputs HotFlip: White-Box Adversarial Examples for Text Classification
Reference 5
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7c7e1f4b-cc74-465c-a073-47852cc6e5dd · outbound
Universal and Context-Independent Triggers for Precise Control of LLM Outputs Imprompter: Tricking LLM Agents into Improper Tool Use
Reference 6
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 0e8044f5-fea4-4d2b-86c2-effa2ae9a732 · outbound
Universal and Context-Independent Triggers for Precise Control of LLM Outputs Retrieval-Augmented Generation for Large Language Models: A Survey
Reference 7
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c42c014b-6220-4ea6-8a3c-29afe667ebba · outbound
Universal and Context-Independent Triggers for Precise Control of LLM Outputs Coercing LLMs to do and reveal (almost) anything
Reference 8
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation d1c591a9-437f-4d01-875d-2987e13891a2 · outbound
Universal and Context-Independent Triggers for Precise Control of LLM Outputs Gradient-based Adversarial Attacks against Text Transformers
Reference 9
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 50d75404-4507-4061-9aeb-1358ca09aded · outbound
Universal and Context-Independent Triggers for Precise Control of LLM Outputs Query-Based Adversarial Prompt Generation
Reference 10
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation fd1a8d26-fe0a-43e5-ae38-709c77b35240 · outbound
Universal and Context-Independent Triggers for Precise Control of LLM Outputs PLeak: Prompt Leaking Attacks against Large Language Model Applications
Reference 11
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e3136544-5010-4aaf-ac09-43d14797c9be · outbound
Universal and Context-Independent Triggers for Precise Control of LLM Outputs A Survey on Large Language Models for Code Generation
Reference 12
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e8c40798-619b-48bd-a0eb-861b8d6af3c8 · outbound
Universal and Context-Independent Triggers for Precise Control of LLM Outputs Automatically Auditing Large Language Models via Discrete Optimization
Reference 13
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 9650219b-7a56-420b-bc35-7fbeef02ad85 · outbound
Universal and Context-Independent Triggers for Precise Control of LLM Outputs Making a SOTA Adversarial Attack on LLMs 38x Faster.https://blog.haizelabs.com/posts/ acg/, 2024
Reference 14
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 35a2ce37-5816-48e3-8c12-d0a416f6b4c9 · outbound
Universal and Context-Independent Triggers for Precise Control of LLM Outputs Rouge: A Package for Automatic Evaluation of Summaries
Reference 15
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 0da94260-2103-466c-9de0-ad1843abbbcf · outbound
Universal and Context-Independent Triggers for Precise Control of LLM Outputs Lost in the Middle: How Language Models Use Long Contexts
Reference 16
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 44f4d0ea-5a36-4aad-b621-1140d5bbc435 · outbound
Universal and Context-Independent Triggers for Precise Control of LLM Outputs AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs
Reference 17
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b36030cd-e2ac-45e4-9103-a8e1508ccd9c · outbound
Universal and Context-Independent Triggers for Precise Control of LLM Outputs Biases in Large Language Models: Origins, Inventory, and Discussion
Reference 18
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 2f021887-f716-4b52-b8a0-9c8a5b2557d7 · outbound
Universal and Context-Independent Triggers for Precise Control of LLM Outputs The OIG Dataset
Reference 19
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 73afde9b-95ea-439a-97dc-beba9c605eed · outbound
Universal and Context-Independent Triggers for Precise Control of LLM Outputs AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs
Reference 20
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 1641d366-5424-425a-b596-247017ceb30e · outbound
Universal and Context-Independent Triggers for Precise Control of LLM Outputs Instruction Tuning with GPT-4
Reference 21
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b9b53e8c-ff55-4d6e-980c-a278b2e148c5 · outbound
Universal and Context-Independent Triggers for Precise Control of LLM Outputs Unresolved cited work
Reference 22
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 99bce508-91f5-40f1-99c7-6c8fd6fdc591 · outbound
Universal and Context-Independent Triggers for Precise Control of LLM Outputs Jailbreaking LLM-Controlled Robots
Reference 23
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation be6e0687-5986-41c9-922f-daf465d9d945 · outbound
Universal and Context-Independent Triggers for Precise Control of LLM Outputs Mathematical discoveries from program search with large language models
Reference 24
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a8a1d384-00f6-415e-8c86-8681e629eba9 · outbound
Universal and Context-Independent Triggers for Precise Control of LLM Outputs Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts
Reference 25
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9babf24f-e280-46eb-bc8c-e74a7f9aa013 · outbound
Universal and Context-Independent Triggers for Precise Control of LLM Outputs The Language Barrier: Dissecting Safety Challenges of LLMs in Multilingual Contexts
Reference 26
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation a06352ee-5b22-4263-ac22-f10169f04f99 · outbound
Universal and Context-Independent Triggers for Precise Control of LLM Outputs AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts
Reference 27
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 35d336ff-8071-459b-b569-e865e999d667 · outbound
Universal and Context-Independent Triggers for Precise Control of LLM Outputs StructuredRAG: JSON Response Formatting with Large Language Models
Reference 28
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9aae8774-f23e-4715-8eb6-12e93613f29b · outbound
Universal and Context-Independent Triggers for Precise Control of LLM Outputs Ben Thompson, and Michael Sklar
Reference 29
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 3440e775-aa96-4ab7-b1bc-49295f27df8e · outbound
Universal and Context-Independent Triggers for Precise Control of LLM Outputs RoleBreak: Character Hallucination as a Jailbreak Attack in Role-Playing Systems
Reference 30
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 880f8d3f-0b18-40fa-b814-168825894c7b · outbound
Universal and Context-Independent Triggers for Precise Control of LLM Outputs Solving olympiad geometry without human demonstrations
Reference 31
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation bcfaaa0f-e955-4027-ba10-bed91477e0a7 · outbound
Universal and Context-Independent Triggers for Precise Control of LLM Outputs Adversarial Attacks on LLMs
Reference 32
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 47db38c8-c849-4f94-91ca-32700e316a31 · outbound
Universal and Context-Independent Triggers for Precise Control of LLM Outputs AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
Reference 33
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 00058a13-17ea-4734-9ec7-4842e9bc1e2c · outbound
Universal and Context-Independent Triggers for Precise Control of LLM Outputs An LLM can Fool Itself: A Prompt-Based Adversarial Attack
Reference 34
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation ebe69a69-653b-4705-a527-d71a1e0f9431 · outbound
Universal and Context-Independent Triggers for Precise Control of LLM Outputs Qwen2 Technical Report
Reference 35
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 294f2f07-f0a7-4ec7-b3a7-b18ef7f01364 · outbound
Universal and Context-Independent Triggers for Precise Control of LLM Outputs GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts
Reference 36
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f0a69176-74bc-4f57-b198-95dca1856bb1 · outbound
Universal and Context-Independent Triggers for Precise Control of LLM Outputs Uncertainty is Fragile: Manipulating Uncertainty in Large Language Models
Reference 37
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation c56295b2-3f01-4aa6-98dc-105c15639e45 · outbound
Universal and Context-Independent Triggers for Precise Control of LLM Outputs How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs
Reference 38
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b3cd7789-069a-4114-8888-f1db13ebdd5e · outbound
Universal and Context-Independent Triggers for Precise Control of LLM Outputs AutoDAN: Interpretable Gradient-Based Adversarial Attacks on Large Language Models
Reference 39
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 3d8d0a79-36f7-4dbe-b31e-bc3839c438ed · outbound
Universal and Context-Independent Triggers for Precise Control of LLM Outputs Universal and Transferable Adversarial Attacks on Aligned Language Models
Reference 40
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b48413b9-c263-4357-9b4b-423464317c1b · inbound
Evaluating Language Models as Synthetic Data Generators Universal and Context-Independent Triggers for Precise Control of LLM Outputs
Reference 22
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation e76b5078-6df0-4a1a-bdee-4d8595648c8d · inbound
Robustness via Referencing: Defending against Prompt Injection Attacks by Referencing the Executed Instruction Universal and Context-Independent Triggers for Precise Control of LLM Outputs
Reference 23
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation ede7cbed-c01c-4a23-a8b9-479048fe8d54 · inbound
Prompt Governance? On Governing Technologies Governed by Natural Language Universal and Context-Independent Triggers for Precise Control of LLM Outputs
Reference 202
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.
Observation 617e5efd-51f7-4608-ba58-8137230741e6 · inbound
Know Your Agent: Reconnaissance-Driven Pentesting of AI Agents Universal and Context-Independent Triggers for Precise Control of LLM Outputs
Reference 31
Source-reported events for the cited work
Unavailable: canonical work link unavailable.