Paper Citation Record · LEDGER

JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs

As of 22 August 2026, this Paper Citation Record lists 42 of 42 outbound references and 3 inbound Pith citation observations for arXiv:2412.15623.

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

pith.paper-citation-record.v1
2412.15623 v1

Coverage vector

measured 42 of 42 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T11:17:49.131015Z

measured 45 of 45 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-04T17:46:19.440645Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-06-29T07:13:16.297937Z

Reference resolution

42 of 42 outbound references displayed

verified exact0
verified fuzzy2
unresolved40
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 6af88e4b-0463-4587-9adb-a98e97fcb927 · outbound

This paper cites GPT-4 Technical Report.

JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs GPT-4 Technical Report

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-11T11:17:48.932972Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12f2a6eb-f3da-48a6-814c-2d6b4a329066 · outbound

This paper cites Detecting Language Model Attacks with Perplexity.

JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs Detecting Language Model Attacks with Perplexity

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-11T11:17:48.938143Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5628e92e-457a-4afb-a72f-f78b17f5a140 · outbound

This paper cites G.; Guo, Z.

JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs G.; Guo, Z

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-11T11:17:48.943269Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2acfd132-0dc6-4439-93ae-e98856297630 · outbound

This paper cites Qwen Technical Report.

JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs Qwen Technical Report

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-11T11:17:48.948353Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 168bfd0a-316d-4120-8615-4698b20260c2 · outbound

This paper cites On the Opportunities and Risks of Foundation Models.

JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs On the Opportunities and Risks of Foundation Models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-11T11:17:48.953494Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 238f35a9-ef22-4939-b519-220aec9528ec · outbound

This paper cites A.; and Terry, M.

JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs A.; and Terry, M

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T11:17:49.702454Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation aac5db27-5d32-468f-8b23-b5d8209259b5 · outbound

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

JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs Jailbreaking Black Box Large Language Models in Twenty Queries

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-11T11:17:48.963693Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 469e2278-cd99-4339-b0e1-c1d0e748ed52 · outbound

This paper cites an unresolved cited work.

JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs Unresolved cited work

Reference 8

Resolution: unresolved; raw_fallback, observed 2026-08-11T11:17:49.690333Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 728c2b89-3e74-416b-8fa6-cbac83fce0f3 · outbound

This paper cites Multilingual Jailbreak Challenges in Large Language Models.

JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs Multilingual Jailbreak Challenges in Large Language Models

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-11T11:17:48.973813Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5865d1d9-33db-4f74-a8c9-2a169c4fbcee · outbound

This paper cites KTO: Model Alignment as Prospect Theoretic Optimization.

JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs KTO: Model Alignment as Prospect Theoretic Optimization

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-11T11:17:48.979129Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6801a13-e451-4995-91f1-611a40a04a97 · outbound

This paper cites A.; Matar, N.; Sowan, B.; Al Khaldy, M.; and Barham, H.

JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs A.; Matar, N.; Sowan, B.; Al Khaldy, M.; and Barham, H

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T11:17:49.679038Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 42b34650-d4e8-4019-a009-6fc9e15caba8 · outbound

This paper cites an unresolved cited work.

JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs Unresolved cited work

Reference 12

Resolution: unresolved; raw_fallback, observed 2026-08-11T11:17:49.666583Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation e877a6fc-77ba-44a0-8685-0b97b9679712 · outbound

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

JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-11T11:17:48.992980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 24ebf4fe-5310-4ecc-a900-d493c13b42e1 · outbound

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

JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs Baseline Defenses for Adversarial Attacks Against Aligned Language Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-11T11:17:48.997434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc0e9486-c296-420f-8cec-e4bce0a2f699 · outbound

This paper cites AI Alignment: A Comprehensive Survey.

JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs AI Alignment: A Comprehensive Survey

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-11T11:17:49.002361Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0557ef9e-4c06-4bf8-9bc8-2687cd2009fc · outbound

This paper cites an unresolved cited work.

JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs Unresolved cited work

Reference 16

Resolution: unresolved; raw_fallback, observed 2026-08-11T11:17:49.655666Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation c03a3bdc-2396-42e6-a34d-6ab8f9af59d4 · outbound

This paper cites Multi-step Jailbreaking Privacy Attacks on ChatGPT.

JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs Multi-step Jailbreaking Privacy Attacks on ChatGPT

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-11T11:17:49.011649Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 824633dc-76df-4737-ac19-52cdbd47e167 · outbound

This paper cites DeepInception: Hypnotize Large Language Model to Be Jailbreaker.

JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs DeepInception: Hypnotize Large Language Model to Be Jailbreaker

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-11T11:17:49.016707Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0392e662-461c-41e5-bbe9-a5b16b01306f · outbound

This paper cites an unresolved cited work.

JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs Unresolved cited work

Reference 19

Resolution: unresolved; raw_fallback, observed 2026-08-11T11:17:49.644753Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 9293c9b8-8dee-47e2-9b81-0a3d9ae76639 · outbound

This paper cites Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study.

JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs Jailbreaking ChatGPT via Prompt Engineering: An Empirical Study

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-11T11:17:49.027329Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7e34296a-7701-469c-a51c-ec0dffb8eec0 · outbound

This paper cites SimPO: Simple Preference Optimization with a Reference-Free Reward.

JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs SimPO: Simple Preference Optimization with a Reference-Free Reward

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-11T11:17:49.032269Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01b7bb61-1a87-4d64-a81d-178a395017dc · outbound

This paper cites an unresolved cited work.

JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs Unresolved cited work

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-11T11:17:49.037916Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f58b3d2-fce9-49ad-b22e-fbb22562a0aa · outbound

This paper cites Red Teaming Language Models with Language Models.

JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs Red Teaming Language Models with Language Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-11T11:17:49.043581Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78dacdc9-dbe9-4076-8d02-912a023e24ca · outbound

This paper cites an unresolved cited work.

JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs Unresolved cited work

Reference 24

Resolution: unresolved; raw_fallback, observed 2026-08-11T11:17:49.626497Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 9803a7e5-5749-453b-bc7c-098d46ebf5bf · outbound

This paper cites D.; Ermon, S.; and Finn, C.

JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs D.; Ermon, S.; and Finn, C

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-11T11:17:49.052422Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e748bb9-50f7-42ba-8c86-6d59fd1dd289 · outbound

This paper cites an unresolved cited work.

JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs Unresolved cited work

Reference 26

Resolution: unresolved; raw_fallback, observed 2026-08-11T11:17:49.607845Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation eb2dddc6-044a-4eee-a744-3e8134cf1f41 · outbound

This paper cites Large Language Model Alignment: A Survey.

JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs Large Language Model Alignment: A Survey

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-11T11:17:49.061766Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6245f067-4c2b-4693-89de-9ae3a6ff5ba4 · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-11T11:17:49.069826Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4e4fe56-7535-424b-b328-10d7df17daf0 · outbound

This paper cites Aligning Large Language Models with Human: A Survey.

JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs Aligning Large Language Models with Human: A Survey

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-11T11:17:49.074644Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d49c7c0-02b0-416a-a604-9eb4492650b8 · outbound

This paper cites an unresolved cited work.

JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs Unresolved cited work

Reference 30

Resolution: unresolved; raw_fallback, observed 2026-08-11T11:17:49.596508Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation a36afdaf-8631-403f-b79d-4c01ef20fcce · outbound

This paper cites an unresolved cited work.

JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs Unresolved cited work

Reference 31

Resolution: unresolved; raw_fallback, observed 2026-08-11T11:17:49.585887Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation bbb33e81-3881-47da-af11-20f837f38f5d · outbound

This paper cites Cognitive Overload: Jailbreaking Large Language Models with Overloaded Logical Thinking.

JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs Cognitive Overload: Jailbreaking Large Language Models with Overloaded Logical Thinking

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-11T11:17:49.088485Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb530ff6-8e8f-44cf-a7f8-d49f313fa476 · outbound

This paper cites A Comprehensive Study of Jailbreak Attack versus Defense for Large Language Models.

JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs A Comprehensive Study of Jailbreak Attack versus Defense for Large Language Models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-11T11:17:49.093000Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 916a2252-3f75-4f40-a54e-6a8d0050f7c2 · outbound

This paper cites an unresolved cited work.

JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs Unresolved cited work

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-11T11:17:49.097099Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d71b151d-cb61-47b7-81fb-bf21d2acfc46 · outbound

This paper cites an unresolved cited work.

JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs Unresolved cited work

Reference 35

Resolution: unresolved; raw_fallback, observed 2026-08-11T11:17:49.568554Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 4a5f5dfe-42d3-458a-9933-33c402fa66f5 · outbound

This paper cites Low-Resource Languages Jailbreak GPT-4.

JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs Low-Resource Languages Jailbreak GPT-4

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-11T11:17:49.105339Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 560d5cea-4212-4f18-9b72-ced4d181817e · outbound

This paper cites GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts.

JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-11T11:17:49.109167Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 137eadbd-56b4-4846-a67d-8e4022145685 · outbound

This paper cites GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher.

JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-11T11:17:49.113067Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ba866eeb-24be-4a4f-ad06-002dc1a6d468 · outbound

This paper cites JADE: A Linguistics-based Safety Evaluation Platform for Large Language Models.

JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs JADE: A Linguistics-based Safety Evaluation Platform for Large Language Models

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-11T11:17:49.117092Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0a73ea6-7be6-4e3f-9b3c-79e9c34d6bbc · outbound

This paper cites Universal and Transferable Adversarial Attacks on Aligned Language Models.

JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-11T11:17:49.121982Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 004e798d-c51f-4a46-8c99-fd46fe2f21c1 · outbound

This paper cites , " * write output.state after.block = add.period write newline.

JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs , " * write output.state after.block = add.period write newline

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-11T11:17:49.126570Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7738d14f-ae98-41a4-87c8-f2e914c06812 · outbound

This paper cites write newline.

JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs write newline

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-11T11:17:49.131015Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation bb2d9b8e-3122-4bbf-bf55-803385c302ec · inbound

LLM in the Middle: A Systematic Review of Threats and Mitigations to Real-World LLM-based Systems cites this paper.

LLM in the Middle: A Systematic Review of Threats and Mitigations to Real-World LLM-based Systems JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs

Reference 175

Resolution: unresolved; no resolver link, observed 2026-08-04T17:46:19.440645Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 050f4c5c-0847-4f91-a0ba-2f68a0cbc320 · inbound

Safety Alignment of LMs via Non-cooperative Games cites this paper.

Safety Alignment of LMs via Non-cooperative Games JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-03T14:24:21.893602Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0bb914fe-945d-4138-8a3f-3b35c25e4e5b · inbound

Evolving Skill-Structured Attack Memory Enhances LLM Jailbreaking cites this paper.

Evolving Skill-Structured Attack Memory Enhances LLM Jailbreaking JailPO: A Novel Black-box Jailbreak Framework via Preference Optimization against Aligned LLMs

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-06-29T07:13:16.299680Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.