Paper Citation Record · LEDGER

Mitigating Deceptive Alignment via Self-Monitoring

As of 8 August 2026, this Paper Citation Record lists 80 of 80 outbound references and 3 inbound Pith citation observations for arXiv:2505.18807.

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

pith.paper-citation-record.v1
2505.18807 v1

Coverage vector

measured 80 of 80 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:30:10.795238Z

measured 83 of 83 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T15:14:22.854339Z

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

80 of 80 outbound references displayed

verified exact0
verified fuzzy17
unresolved63
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

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

Outbound references

Observation 83677165-82a4-4664-bd97-21887015e19b · outbound

This paper cites Introducing openai o1-preview.

Mitigating Deceptive Alignment via Self-Monitoring Introducing openai o1-preview

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:30:18.690887Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation bc6cad5f-5a5d-4302-82d2-65ce6a296a0b · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

Mitigating Deceptive Alignment via Self-Monitoring DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:04.060422Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51cf49de-8586-462c-bddf-9c41241e9cc2 · outbound

This paper cites Chain-of-thought prompting elicits reasoning in large language models.

Mitigating Deceptive Alignment via Self-Monitoring Chain-of-thought prompting elicits reasoning in large language models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:04.114784Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09c55401-661d-49d0-848f-bfa1201258ca · outbound

This paper cites AI Alignment: A Comprehensive Survey.

Mitigating Deceptive Alignment via Self-Monitoring AI Alignment: A Comprehensive Survey

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:04.196418Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc773ee9-4491-4355-afb5-143fe9e19624 · outbound

This paper cites Risks from Learned Optimization in Advanced Machine Learning Systems.

Mitigating Deceptive Alignment via Self-Monitoring Risks from Learned Optimization in Advanced Machine Learning Systems

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:04.260470Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80a65e4f-f2a7-4382-b739-6637b0c24c72 · outbound

This paper cites Frontier Models are Capable of In-context Scheming.

Mitigating Deceptive Alignment via Self-Monitoring Frontier Models are Capable of In-context Scheming

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:04.319823Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c2bc9d3-9b3a-4bd8-a2df-7f37c0a94918 · outbound

This paper cites Foundational Challenges in Assuring Alignment and Safety of Large Language Models.

Mitigating Deceptive Alignment via Self-Monitoring Foundational Challenges in Assuring Alignment and Safety of Large Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:04.428012Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 904a83a5-b850-4e07-b3f5-645ad7b05482 · outbound

This paper cites Language Models Learn to Mislead Humans via RLHF.

Mitigating Deceptive Alignment via Self-Monitoring Language Models Learn to Mislead Humans via RLHF

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:04.463941Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3bda92d4-c08e-4a48-90b0-53f4e7113efb · outbound

This paper cites Managing extreme ai risks amid rapid progress.

Mitigating Deceptive Alignment via Self-Monitoring Managing extreme ai risks amid rapid progress

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:04.536207Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1c7d851-abb7-46c1-ad89-0635acd982e8 · outbound

This paper cites Privacy risks of general-purpose language models.

Mitigating Deceptive Alignment via Self-Monitoring Privacy risks of general-purpose language models

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:30:18.514680Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 098f5cbd-18e0-4689-9dbb-e7359454e794 · outbound

This paper cites Frontier AI systems have surpassed the self-replicating red line.

Mitigating Deceptive Alignment via Self-Monitoring Frontier AI systems have surpassed the self-replicating red line

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:04.787401Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0b4bd89-2800-4f79-8679-5371b3c50fe4 · outbound

This paper cites Alignment faking in large language models.

Mitigating Deceptive Alignment via Self-Monitoring Alignment faking in large language models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:04.868190Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2fa7d15b-f588-41bb-b358-f85bac93806f · outbound

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

Mitigating Deceptive Alignment via Self-Monitoring Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:04.987930Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26c081fb-2fb4-4bc7-a133-8512d908309b · outbound

This paper cites Darkbench: Benchmarking dark patterns in large language models.

Mitigating Deceptive Alignment via Self-Monitoring Darkbench: Benchmarking dark patterns in large language models

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:30:18.182736Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 40edb399-1f95-4346-86e6-090ebf81128c · outbound

This paper cites Evaluating the Paperclip Maximizer: Are RL-Based Language Models More Likely to Pursue Instrumental Goals?.

Mitigating Deceptive Alignment via Self-Monitoring Evaluating the Paperclip Maximizer: Are RL-Based Language Models More Likely to Pursue Instrumental Goals?

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:05.120166Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 673ccd70-0688-48b4-b0f3-f48a23bd1dec · outbound

This paper cites Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training.

Mitigating Deceptive Alignment via Self-Monitoring Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:05.188094Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d4e3e7a-8f66-4be0-b3fd-1477604c2cd2 · outbound

This paper cites International AI Safety Report.

Mitigating Deceptive Alignment via Self-Monitoring International AI Safety Report

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:05.234059Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ee0c132-066c-4f33-832b-40e96438b21d · outbound

This paper cites Language models don’t always say what they think: Unfaithful explanations in chain-of-thought prompting.

Mitigating Deceptive Alignment via Self-Monitoring Language models don’t always say what they think: Unfaithful explanations in chain-of-thought prompting

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:05.260854Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d9afa334-7493-405b-b63e-a82a78f5d73c · outbound

This paper cites Policy Frameworks for Transparent Chain-of-Thought Reasoning in Large Language Models.

Mitigating Deceptive Alignment via Self-Monitoring Policy Frameworks for Transparent Chain-of-Thought Reasoning in Large Language Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:05.298607Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0e2b95f-069b-4d5f-b70c-6d85580017cf · outbound

This paper cites Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation.

Mitigating Deceptive Alignment via Self-Monitoring Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:05.384371Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bea15da7-e936-4cbd-84b6-7fe78ea1b9a9 · outbound

This paper cites From System 1 to System 2: A Survey of Reasoning Large Language Models.

Mitigating Deceptive Alignment via Self-Monitoring From System 1 to System 2: A Survey of Reasoning Large Language Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:05.477915Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e12a21ad-c180-41f2-a85f-4a0d1874be96 · outbound

This paper cites Markov decision processes: discrete stochastic dynamic programming.

Mitigating Deceptive Alignment via Self-Monitoring Markov decision processes: discrete stochastic dynamic programming

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:05.595053Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8694ca25-0e87-4150-a6e4-bd758a5fc61b · outbound

This paper cites Reinforcement learning: An introduction, volume 1.

Mitigating Deceptive Alignment via Self-Monitoring Reinforcement learning: An introduction, volume 1

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:05.716513Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02639ee0-cd8c-40c4-8bb0-31684ae7ceef · outbound

This paper cites Training language models to follow instructions with human feedback.

Mitigating Deceptive Alignment via Self-Monitoring Training language models to follow instructions with human feedback

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:05.874104Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e9cdb46-9f25-447e-ad2f-6c6f25721ab5 · outbound

This paper cites Direct preference optimization: Your language model is secretly a reward model.

Mitigating Deceptive Alignment via Self-Monitoring Direct preference optimization: Your language model is secretly a reward model

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:05.978324Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1cb8ea0a-c44f-461f-a6cc-02ebeb23f7bc · outbound

This paper cites Handbook of constraint programming.

Mitigating Deceptive Alignment via Self-Monitoring Handbook of constraint programming

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:30:17.898223Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation c4c02e54-93f3-4779-a680-44c8d90d28b3 · outbound

This paper cites Defining and characterizing reward gaming.

Mitigating Deceptive Alignment via Self-Monitoring Defining and characterizing reward gaming

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:06.349381Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bbc388a2-87a0-4fde-9edf-57ab6eb42b11 · outbound

This paper cites Cooperative inverse reinforcement learning.

Mitigating Deceptive Alignment via Self-Monitoring Cooperative inverse reinforcement learning

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:06.469580Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d808a0c0-e5fe-4fb5-a4aa-514fa1f54ebb · outbound

This paper cites BAMDP Shaping: a Unified Framework for Intrinsic Motivation and Reward Shaping.

Mitigating Deceptive Alignment via Self-Monitoring BAMDP Shaping: a Unified Framework for Intrinsic Motivation and Reward Shaping

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:06.590347Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 86531776-8121-4847-a77f-a686ddc8d381 · outbound

This paper cites Defin- ing deception in decision making.

Mitigating Deceptive Alignment via Self-Monitoring Defin- ing deception in decision making

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:30:17.681852Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ad4c6467-25ae-475c-adb0-b0f148400b61 · outbound

This paper cites Machine behaviour.

Mitigating Deceptive Alignment via Self-Monitoring Machine behaviour

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:30:17.491130Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 6c98cc28-959e-44be-825c-ae5533d4ef4f · outbound

This paper cites The off-switch game.

Mitigating Deceptive Alignment via Self-Monitoring The off-switch game

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:06.923371Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9bf5cbbd-9f3b-430e-9c08-8eb0167ba75e · outbound

This paper cites Comparison of the predicted and observed secondary structure of t4 phage lysozyme.

Mitigating Deceptive Alignment via Self-Monitoring Comparison of the predicted and observed secondary structure of t4 phage lysozyme

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:07.044879Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ed211ab-159a-4316-92c1-6b1f540e8132 · outbound

This paper cites Ai deception: A survey of examples, risks, and potential solutions.

Mitigating Deceptive Alignment via Self-Monitoring Ai deception: A survey of examples, risks, and potential solutions

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:30:17.165031Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation d31cd9fc-fdc5-4c26-9a4d-7a62511ab327 · outbound

This paper cites Discovering Language Model Behaviors with Model-Written Evaluations.

Mitigating Deceptive Alignment via Self-Monitoring Discovering Language Model Behaviors with Model-Written Evaluations

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:07.287960Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 685d6827-be15-4b6c-84e1-37ea8a7cc513 · outbound

This paper cites Deception abilities emerged in large language models.

Mitigating Deceptive Alignment via Self-Monitoring Deception abilities emerged in large language models

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:30:16.932491Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 8b5604c4-b415-429d-9b2f-96d25e8a2650 · outbound

This paper cites Opendeception: Benchmarking and investigating ai deceptive behaviors via open-ended interaction simulation.

Mitigating Deceptive Alignment via Self-Monitoring Opendeception: Benchmarking and investigating ai deceptive behaviors via open-ended interaction simulation

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:07.532498Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c515169-f120-4524-803e-06527d6e6a72 · outbound

This paper cites The mask benchmark: Disentangling honesty from accuracy in ai systems.

Mitigating Deceptive Alignment via Self-Monitoring The mask benchmark: Disentangling honesty from accuracy in ai systems

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:07.579875Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d88fc10-a4fe-4c1c-ba7e-dbd916a8a361 · outbound

This paper cites AI Sandbagging: Language Models can Strategically Underperform on Evaluations.

Mitigating Deceptive Alignment via Self-Monitoring AI Sandbagging: Language Models can Strategically Underperform on Evaluations

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:07.610336Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd02a31d-0f35-4579-9b8f-5b8b097f32bb · outbound

This paper cites Judging llm-as-a-judge with mt-bench and chatbot arena.

Mitigating Deceptive Alignment via Self-Monitoring Judging llm-as-a-judge with mt-bench and chatbot arena

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:07.652785Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a4bb438-6855-4973-90bc-3a8d6ef00006 · outbound

This paper cites an unresolved cited work.

Mitigating Deceptive Alignment via Self-Monitoring Unresolved cited work

Reference 46

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:30:16.411365Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ac63f8ae-d62e-4aaf-a772-6abce6e67dea · outbound

This paper cites Qwen2 Technical Report.

Mitigating Deceptive Alignment via Self-Monitoring Qwen2 Technical Report

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:07.823125Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e534c1d-7c36-4336-8cc4-2b002bfe056f · outbound

This paper cites The Llama 3 Herd of Models.

Mitigating Deceptive Alignment via Self-Monitoring The Llama 3 Herd of Models

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:07.921367Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c22dd63e-af11-4ad2-b88f-6ea63dee549f · outbound

This paper cites Claude 3.

Mitigating Deceptive Alignment via Self-Monitoring Claude 3

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:30:15.968293Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 650038e4-2c1c-4935-9d89-d919d8f4e149 · outbound

This paper cites Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context.

Mitigating Deceptive Alignment via Self-Monitoring Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:08.031978Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1bb9ac23-60fb-4b1e-91d0-09e9e5697d2a · outbound

This paper cites Learning to reason with llms.

Mitigating Deceptive Alignment via Self-Monitoring Learning to reason with llms

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:30:15.760571Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 26d25d22-bf8b-4db2-b18a-26c2de8171b7 · outbound

This paper cites A StrongREJECT for Empty Jailbreaks.

Mitigating Deceptive Alignment via Self-Monitoring A StrongREJECT for Empty Jailbreaks

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:08.125239Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0fed44a-7184-4cd2-8445-b67569db6ca0 · outbound

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

Mitigating Deceptive Alignment via Self-Monitoring Jailbreaking Black Box Large Language Models in Twenty Queries

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:08.164673Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e02df15-0093-4537-846e-9a9121732df3 · outbound

This paper cites How johnny can persuade llms to jailbreak them: Rethinking persuasion to challenge ai safety by humanizing llms.

Mitigating Deceptive Alignment via Self-Monitoring How johnny can persuade llms to jailbreak them: Rethinking persuasion to challenge ai safety by humanizing llms

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:08.215835Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 48f8a6d5-94b4-4ccf-a350-a4e7af0ace1c · outbound

This paper cites Towards evaluating the robustness of neural networks.

Mitigating Deceptive Alignment via Self-Monitoring Towards evaluating the robustness of neural networks

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:08.261749Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2cab175-f615-481b-ba71-1124f375c68e · outbound

This paper cites Safety Alignment Should Be Made More Than Just a Few Tokens Deep.

Mitigating Deceptive Alignment via Self-Monitoring Safety Alignment Should Be Made More Than Just a Few Tokens Deep

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:08.313927Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fda382d3-d322-45a7-b5c5-00d39135fdbc · outbound

This paper cites JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models.

Mitigating Deceptive Alignment via Self-Monitoring JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:08.351856Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 533de5ff-de66-4a20-bafc-ba2d1bba421f · outbound

This paper cites Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations.

Mitigating Deceptive Alignment via Self-Monitoring Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:08.405155Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ea2b524-9826-4f34-b090-b916f1f22b6b · outbound

This paper cites Beavertails: Towards improved safety alignment of llm via a human-preference dataset.

Mitigating Deceptive Alignment via Self-Monitoring Beavertails: Towards improved safety alignment of llm via a human-preference dataset

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:30:18.366017Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation d66ec9ff-2935-4e0f-b5a2-1b45b0df9e93 · outbound

This paper cites SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities.

Mitigating Deceptive Alignment via Self-Monitoring SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:08.592130Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99bc8ee5-75f0-47a8-901b-81b7d3569418 · outbound

This paper cites Star-1: Safer alignment of reasoning llms with 1k data.

Mitigating Deceptive Alignment via Self-Monitoring Star-1: Safer alignment of reasoning llms with 1k data

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:08.656029Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46f8839c-2343-4faa-a81c-bff59ebf220b · outbound

This paper cites Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment.

Mitigating Deceptive Alignment via Self-Monitoring Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignment

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:08.770366Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8cc94936-efae-4f41-aa47-78820d0edf70 · outbound

This paper cites Ultrafeedback: Boosting language models with high-quality feedback, 2023.

Mitigating Deceptive Alignment via Self-Monitoring Ultrafeedback: Boosting language models with high-quality feedback, 2023

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:30:15.472718Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 3497f84f-f0a4-42cb-9109-81ca5c60952d · outbound

This paper cites an unresolved cited work.

Mitigating Deceptive Alignment via Self-Monitoring Unresolved cited work

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:08.994148Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3430b97-bf70-4334-aa64-08557737abde · outbound

This paper cites Constrained Markov decision processes.

Mitigating Deceptive Alignment via Self-Monitoring Constrained Markov decision processes

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-07T14:30:09.107586Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e7d481e-0a70-48e3-945c-2d83ececa2f4 · outbound

This paper cites mesa-objective.

Mitigating Deceptive Alignment via Self-Monitoring mesa-objective

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:30:15.114338Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 7500718a-9539-4b1a-a869-0c1a98a9e116 · outbound

This paper cites an unresolved cited work.

Mitigating Deceptive Alignment via Self-Monitoring Unresolved cited work

Reference 67

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:30:15.002661Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ba78bc72-891b-45c9-b232-1101adb05da0 · outbound

This paper cites an unresolved cited work.

Mitigating Deceptive Alignment via Self-Monitoring Unresolved cited work

Reference 68

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:30:14.833649Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation f69279a8-86bb-4350-a036-2c587f32de1c · outbound

This paper cites an unresolved cited work.

Mitigating Deceptive Alignment via Self-Monitoring Unresolved cited work

Reference 69

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:30:14.666887Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation f4bc6367-5801-4399-b33f-207e1df98019 · outbound

This paper cites an unresolved cited work.

Mitigating Deceptive Alignment via Self-Monitoring Unresolved cited work

Reference 70

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:30:14.481276Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 8d054452-f45a-408d-b5a9-3fb0db8c3546 · outbound

This paper cites an unresolved cited work.

Mitigating Deceptive Alignment via Self-Monitoring Unresolved cited work

Reference 71

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:30:14.329443Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation a8545292-e801-46c7-a6ae-6b221bbfeaab · outbound

This paper cites chain of thought.

Mitigating Deceptive Alignment via Self-Monitoring chain of thought

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:30:14.164721Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 020d917c-44c9-46fe-83de-b2d4b7f006bf · outbound

This paper cites an unresolved cited work.

Mitigating Deceptive Alignment via Self-Monitoring Unresolved cited work

Reference 73

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:30:14.045298Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation d2c28ae8-476c-411b-9ac3-81a609db852d · outbound

This paper cites an unresolved cited work.

Mitigating Deceptive Alignment via Self-Monitoring Unresolved cited work

Reference 74

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:30:13.876029Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 7cfbc82d-51ea-4249-946d-ed8460f0c9e9 · outbound

This paper cites an unresolved cited work.

Mitigating Deceptive Alignment via Self-Monitoring Unresolved cited work

Reference 75

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:30:13.685770Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 1cc208bf-4559-4220-9bdb-d0766d879914 · outbound

This paper cites an unresolved cited work.

Mitigating Deceptive Alignment via Self-Monitoring Unresolved cited work

Reference 76

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:30:13.546728Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 1b4e8e1a-66d9-46c1-b32c-f320f8076147 · outbound

This paper cites chain of thought.

Mitigating Deceptive Alignment via Self-Monitoring chain of thought

Reference 77

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:30:13.355400Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 5eed0c7b-3a3a-40ed-8223-09aeb0fcf508 · outbound

This paper cites an unresolved cited work.

Mitigating Deceptive Alignment via Self-Monitoring Unresolved cited work

Reference 78

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:30:13.215196Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 19fc4678-13dd-486c-9473-277dcab5fab2 · outbound

This paper cites an unresolved cited work.

Mitigating Deceptive Alignment via Self-Monitoring Unresolved cited work

Reference 79

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:30:13.067265Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 084a442c-29f4-4fd5-a99b-dba0cb5a1841 · outbound

This paper cites an unresolved cited work.

Mitigating Deceptive Alignment via Self-Monitoring Unresolved cited work

Reference 80

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:30:12.949466Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 09e40250-bbb1-4fb8-a9a8-4ca82c464cd5 · outbound

This paper cites This must be distinguished from uninten- tional inaccuracies arising from simple technical errors, knowledge limitations, or inherent capability gaps.

Mitigating Deceptive Alignment via Self-Monitoring This must be distinguished from uninten- tional inaccuracies arising from simple technical errors, knowledge limitations, or inherent capability gaps

Reference 81

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:30:12.786270Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 98d2a5ca-503b-499b-ad09-3135902eba66 · outbound

This paper cites an unresolved cited work.

Mitigating Deceptive Alignment via Self-Monitoring Unresolved cited work

Reference 82

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:30:12.611103Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 00734278-e006-4fce-8747-3ecf4e28ab9c · outbound

This paper cites It requires a comprehensive analysis that incorporates the specific question posed by the user, the settings of the interaction scenario, and the full context of the dialogue.

Mitigating Deceptive Alignment via Self-Monitoring It requires a comprehensive analysis that incorporates the specific question posed by the user, the settings of the interaction scenario, and the full context of the dialogue

Reference 83

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:30:12.449721Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 237cd224-9547-4065-9e3a-d51b130ed1a0 · outbound

This paper cites an unresolved cited work.

Mitigating Deceptive Alignment via Self-Monitoring Unresolved cited work

Reference 84

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:30:12.282860Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation aafde672-fa70-42af-b05d-3cd87a1c3c64 · outbound

This paper cites an unresolved cited work.

Mitigating Deceptive Alignment via Self-Monitoring Unresolved cited work

Reference 85

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:30:12.111009Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Pith citing papers

Observation 50541677-0d41-417a-94bd-ff30d9a909d5 · inbound

Frontier AI Risk Management Framework in Practice: A Risk Analysis Technical Report cites this paper.

Frontier AI Risk Management Framework in Practice: A Risk Analysis Technical Report Mitigating Deceptive Alignment via Self-Monitoring

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T15:14:22.854339Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6261264-1330-46ef-b544-535ee79766d2 · inbound

Dissociative Identity: Language Model Agents Lack Grounding for Reputation Mechanisms cites this paper.

Dissociative Identity: Language Model Agents Lack Grounding for Reputation Mechanisms Mitigating Deceptive Alignment via Self-Monitoring

Reference 67

Resolution: verified exact; arxiv_id, observed 2026-06-29T00:32:53.204147Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 1a36a228-ee59-44e3-8cfa-6360fc35e8dc · inbound

Manipulation Is Task-Dependent: A Multi-Axis, Multi-Environment Evaluation of Frontier LLMs cites this paper.

Manipulation Is Task-Dependent: A Multi-Axis, Multi-Environment Evaluation of Frontier LLMs Mitigating Deceptive Alignment via Self-Monitoring

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-07-04T21:00:10.043768Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.