Paper Citation Record · LEDGER

From Rogue to Safe AI: The Role of Explicit Refusals in Aligning LLMs with International Humanitarian Law

As of 23 August 2026, this Paper Citation Record lists 36 of 36 outbound references and 0 inbound Pith citation observations for arXiv:2506.06391.

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

pith.paper-citation-record.v1
2506.06391 v1

Coverage vector

measured 36 of 36 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T10:28:55.461862Z

measured 36 of 36 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-23T06:30:58.430688+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

36 of 36 outbound references displayed

verified exact10
verified fuzzy6
unresolved18
parse uncertain0
malformed identifier2
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 574a406c-f831-4253-9fb6-7e3a53640357 · outbound

This paper cites an unresolved cited work.

From Rogue to Safe AI: The Role of Explicit Refusals in Aligning LLMs with International Humanitarian Law Unresolved cited work

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:52.334141Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60a6e142-cd78-4ee0-b820-07d5935e4212 · outbound

This paper cites The Radicalization Risks of GPT-3 and Advanced Neural Language Models.

From Rogue to Safe AI: The Role of Explicit Refusals in Aligning LLMs with International Humanitarian Law The Radicalization Risks of GPT-3 and Advanced Neural Language Models

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:52.406815Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 28f4630a-852f-4e1f-8119-cd5238a65cdf · outbound

This paper cites Klyman, ‘Acceptable Use Policies for Foundation Models’, Proceedings of the AAAI/ACM Conference on AI, Ethics, and So- ciety, vol.

From Rogue to Safe AI: The Role of Explicit Refusals in Aligning LLMs with International Humanitarian Law Klyman, ‘Acceptable Use Policies for Foundation Models’, Proceedings of the AAAI/ACM Conference on AI, Ethics, and So- ciety, vol

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:52.513958Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4358394e-7cca-4282-b6d5-daa2227aa4db · outbound

This paper cites Henckaerts and L.

From Rogue to Safe AI: The Role of Explicit Refusals in Aligning LLMs with International Humanitarian Law Henckaerts and L

Reference 4

Resolution: verified exact; doi, observed 2026-08-07T10:28:57.751025Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 7ac05577-70b5-4328-ab54-c0e57ca6e660 · outbound

This paper cites As an AI language model, I cannot.

From Rogue to Safe AI: The Role of Explicit Refusals in Aligning LLMs with International Humanitarian Law As an AI language model, I cannot

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:52.675257Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c19d996-7c95-40ef-8887-1083d2e49e11 · outbound

This paper cites Constitutional AI: Harmlessness from AI Feedback.

From Rogue to Safe AI: The Role of Explicit Refusals in Aligning LLMs with International Humanitarian Law Constitutional AI: Harmlessness from AI Feedback

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:52.769177Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34896cab-3e45-46f0-b59a-f53c3fcb04d0 · outbound

This paper cites Don't Say No: Jailbreaking LLM by Suppressing Refusal.

From Rogue to Safe AI: The Role of Explicit Refusals in Aligning LLMs with International Humanitarian Law Don't Say No: Jailbreaking LLM by Suppressing Refusal

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:52.855847Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2ce047c-3d2a-4395-bd65-600f955b599d · outbound

This paper cites Milaninia, ‘Biases in machine learning models and big data analytics: The inter- national criminal and humanitarian law im- plications’, Int.

From Rogue to Safe AI: The Role of Explicit Refusals in Aligning LLMs with International Humanitarian Law Milaninia, ‘Biases in machine learning models and big data analytics: The inter- national criminal and humanitarian law im- plications’, Int

Reference 8

Resolution: verified exact; doi, observed 2026-08-07T10:28:57.481074Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 8443e5a1-ed35-40cf-8bee-b3ceebed01cd · outbound

This paper cites an unresolved cited work.

From Rogue to Safe AI: The Role of Explicit Refusals in Aligning LLMs with International Humanitarian Law Unresolved cited work

Reference 9

Resolution: unresolved; raw_fallback, observed 2026-08-07T10:29:00.820672Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 45affa65-05f6-4f1c-bf7a-c1414ae12f0b · outbound

This paper cites Marcos, ‘Can large language models apply the law?’, AI and Society, pp.

From Rogue to Safe AI: The Role of Explicit Refusals in Aligning LLMs with International Humanitarian Law Marcos, ‘Can large language models apply the law?’, AI and Society, pp

Reference 10

Resolution: verified exact; doi, observed 2026-08-07T10:28:57.323876Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 12450b47-255a-49f7-ac2c-8d758ae66a99 · outbound

This paper cites Available: https://www.ohchr.org/en/instruments-and- mechanisms/international-human-rights-law.

From Rogue to Safe AI: The Role of Explicit Refusals in Aligning LLMs with International Humanitarian Law Available: https://www.ohchr.org/en/instruments-and- mechanisms/international-human-rights-law

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:29:00.597138Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 3e759a0d-f949-4320-bb48-db40320f9f66 · outbound

This paper cites Available: https://www.ohchr.org/en/resources/educato rs/human-rights-education-training/universal- declaration-human-rights-1948.

From Rogue to Safe AI: The Role of Explicit Refusals in Aligning LLMs with International Humanitarian Law Available: https://www.ohchr.org/en/resources/educato rs/human-rights-education-training/universal- declaration-human-rights-1948

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:29:00.270595Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 3165029b-0832-4650-80b5-55033597d551 · outbound

This paper cites Available: https://civil-protection-humanitarian- aid.ec.europa.eu/what/humanitarian- aid/international-humanitarian-law.

From Rogue to Safe AI: The Role of Explicit Refusals in Aligning LLMs with International Humanitarian Law Available: https://civil-protection-humanitarian- aid.ec.europa.eu/what/humanitarian- aid/international-humanitarian-law

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:29:00.037168Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation cd085da7-8493-4990-bbf8-e2f95ebbc257 · outbound

This paper cites MacLaren and F.

From Rogue to Safe AI: The Role of Explicit Refusals in Aligning LLMs with International Humanitarian Law MacLaren and F

Reference 14

Resolution: verified exact; doi, observed 2026-08-07T10:28:57.065163Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 5d3d0bd1-5305-4e1f-a526-c2f80c6b4fe7 · outbound

This paper cites Zhang, M.

From Rogue to Safe AI: The Role of Explicit Refusals in Aligning LLMs with International Humanitarian Law Zhang, M

Reference 15

Resolution: verified exact; doi, observed 2026-08-07T10:28:56.915104Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 65ccd62e-d953-4566-8f4a-68a419aa1c14 · outbound

This paper cites Refusal Behavior in Large Language Models: A Nonlinear Perspective.

From Rogue to Safe AI: The Role of Explicit Refusals in Aligning LLMs with International Humanitarian Law Refusal Behavior in Large Language Models: A Nonlinear Perspective

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:53.629021Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9e61acd-30ff-4dbb-9931-d312de3603c9 · outbound

This paper cites Does Refusal Training in LLMs Generalize to the Past Tense?.

From Rogue to Safe AI: The Role of Explicit Refusals in Aligning LLMs with International Humanitarian Law Does Refusal Training in LLMs Generalize to the Past Tense?

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:53.683286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ca58ba4-11fb-4382-a51a-9873aae6d3e4 · outbound

This paper cites an unresolved cited work.

From Rogue to Safe AI: The Role of Explicit Refusals in Aligning LLMs with International Humanitarian Law Unresolved cited work

Reference 18

Resolution: unresolved; raw_fallback, observed 2026-08-07T10:28:59.670807Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation ddeb866e-b736-45a1-ba20-8621612a8231 · outbound

This paper cites Pomson, ‘Methodology of identifying cus- tomary international law applicable to cyber activities’, LeidenJournalofInternationalLaw, vol.

From Rogue to Safe AI: The Role of Explicit Refusals in Aligning LLMs with International Humanitarian Law Pomson, ‘Methodology of identifying cus- tomary international law applicable to cyber activities’, LeidenJournalofInternationalLaw, vol

Reference 19

Resolution: verified exact; doi, observed 2026-08-07T10:28:56.616471Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 40d66404-5b12-4fde-ba51-478a18715cb4 · outbound

This paper cites Yudkowsky, ‘The AI Alignment Prob- lem: Why It’s Hard, and Where to Start’.

From Rogue to Safe AI: The Role of Explicit Refusals in Aligning LLMs with International Humanitarian Law Yudkowsky, ‘The AI Alignment Prob- lem: Why It’s Hard, and Where to Start’

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:28:59.339063Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 315cca8b-bb6b-4a48-8416-01e8c44dad0e · outbound

This paper cites Gabriel, ‘Artificial Intelligence, Values, and Alignment’, Minds and Machines, vol.

From Rogue to Safe AI: The Role of Explicit Refusals in Aligning LLMs with International Humanitarian Law Gabriel, ‘Artificial Intelligence, Values, and Alignment’, Minds and Machines, vol

Reference 21

Resolution: malformed identifier; no resolver link, observed 2026-08-07T10:28:54.089537Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25992e24-38b4-4f99-bd6d-29bf0b781559 · outbound

This paper cites an unresolved cited work.

From Rogue to Safe AI: The Role of Explicit Refusals in Aligning LLMs with International Humanitarian Law Unresolved cited work

Reference 22

Resolution: unresolved; raw_fallback, observed 2026-08-07T10:28:58.947214Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 20671a0a-4bb0-4bc0-bdfb-d614d4463660 · outbound

This paper cites an unresolved cited work.

From Rogue to Safe AI: The Role of Explicit Refusals in Aligning LLMs with International Humanitarian Law Unresolved cited work

Reference 23

Resolution: unresolved; raw_fallback, observed 2026-08-07T10:28:58.661986Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation aeea0786-0e18-48f6-9888-f708798daa3b · outbound

This paper cites International Scientific Report on the Safety of Advanced AI (Interim Report).

From Rogue to Safe AI: The Role of Explicit Refusals in Aligning LLMs with International Humanitarian Law International Scientific Report on the Safety of Advanced AI (Interim Report)

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:54.373523Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4130bbd-beee-4440-986e-657d2eec1104 · outbound

This paper cites Strzępek, ‘Human Rights as a Factor in the AI Alignment’, GIS Odyssey Journal, vol.

From Rogue to Safe AI: The Role of Explicit Refusals in Aligning LLMs with International Humanitarian Law Strzępek, ‘Human Rights as a Factor in the AI Alignment’, GIS Odyssey Journal, vol

Reference 25

Resolution: verified exact; doi, observed 2026-08-07T10:28:56.407578Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 4f2251a5-a415-4c12-b106-67f98b8ce38b · outbound

This paper cites Szpor, ‘European Legal Framework for the Use of Artificial Intelligence in Pub- licly Accessible Space’, GIS Odyssey Journal, vol.

From Rogue to Safe AI: The Role of Explicit Refusals in Aligning LLMs with International Humanitarian Law Szpor, ‘European Legal Framework for the Use of Artificial Intelligence in Pub- licly Accessible Space’, GIS Odyssey Journal, vol

Reference 26

Resolution: verified exact; doi, observed 2026-08-07T10:28:56.199379Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation a0548506-e31e-4e21-91d2-9ec7121100b2 · outbound

This paper cites Novelli, F.

From Rogue to Safe AI: The Role of Explicit Refusals in Aligning LLMs with International Humanitarian Law Novelli, F

Reference 27

Resolution: malformed identifier; no resolver link, observed 2026-08-07T10:28:54.645387Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eef5aa8c-12ea-43a2-b88e-362704391942 · outbound

This paper cites Ji et al., ‘BeaverTails: Towards Im- proved Safety Alignment of LLM via a Human-Preference Dataset’, Nov.

From Rogue to Safe AI: The Role of Explicit Refusals in Aligning LLMs with International Humanitarian Law Ji et al., ‘BeaverTails: Towards Im- proved Safety Alignment of LLM via a Human-Preference Dataset’, Nov

Reference 28

Resolution: verified exact; doi, observed 2026-08-07T10:28:56.024830Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation c0f879a3-92f5-496f-abec-9b8f05638b4d · outbound

This paper cites ToxicChat: Unveiling Hidden Challenges of Toxicity Detection in Real-World User-AI Conversation.

From Rogue to Safe AI: The Role of Explicit Refusals in Aligning LLMs with International Humanitarian Law ToxicChat: Unveiling Hidden Challenges of Toxicity Detection in Real-World User-AI Conversation

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:54.802416Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e333f84-534b-47cf-826d-86effaff999f · outbound

This paper cites https://platform.openai.com.

From Rogue to Safe AI: The Role of Explicit Refusals in Aligning LLMs with International Humanitarian Law https://platform.openai.com

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:28:58.482180Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 14de37fd-3c28-4821-adbe-efc2d4d0a818 · outbound

This paper cites OR-Bench: An Over-Refusal Benchmark for Large Language Models.

From Rogue to Safe AI: The Role of Explicit Refusals in Aligning LLMs with International Humanitarian Law OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:54.986950Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea34ee52-42ec-4c1e-ae5d-96a5e1f37298 · outbound

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

From Rogue to Safe AI: The Role of Explicit Refusals in Aligning LLMs with International Humanitarian Law Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:55.100445Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19f8fb8a-0a31-4957-a2da-2040eaa170a2 · outbound

This paper cites ThinkGuard: Deliberative Slow Thinking Leads to Cautious Guardrails.

From Rogue to Safe AI: The Role of Explicit Refusals in Aligning LLMs with International Humanitarian Law ThinkGuard: Deliberative Slow Thinking Leads to Cautious Guardrails

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:55.208535Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af9d2d6b-db8e-4234-86da-380e59faee2c · outbound

This paper cites Stanovsky, R.

From Rogue to Safe AI: The Role of Explicit Refusals in Aligning LLMs with International Humanitarian Law Stanovsky, R

Reference 34

Resolution: verified exact; doi, observed 2026-08-07T10:28:55.714860Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation c6970e34-3663-4ae1-9c1e-4db664fc4553 · outbound

This paper cites Scheutz, R.

From Rogue to Safe AI: The Role of Explicit Refusals in Aligning LLMs with International Humanitarian Law Scheutz, R

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T10:28:55.374050Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ed424fb-6b34-4866-ac7e-41c3de476ada · outbound

This paper cites Claude 3.7 system card.

From Rogue to Safe AI: The Role of Explicit Refusals in Aligning LLMs with International Humanitarian Law Claude 3.7 system card

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T10:28:58.271519Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Pith citing papers

No inbound Pith citation observations are available.