Paper Citation Record · LEDGER

Lifelong Safety Alignment for Language Models

As of 7 August 2026, this Paper Citation Record lists 80 of 80 outbound references and 3 inbound Pith citation observations for arXiv:2505.20259.

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

pith.paper-citation-record.v1
2505.20259 v1

Coverage vector

measured 80 of 80 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T14:00:11.823481Z

measured 83 of 83 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-04T23:10:46.332617Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-21T06:19:41.953726Z

Reference resolution

80 of 80 outbound references displayed

verified exact1
verified fuzzy13
unresolved66
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 1a49d225-c6b9-4970-adc6-1f49221a6a08 · outbound

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

Lifelong Safety Alignment for Language Models Does Refusal Training in LLMs Generalize to the Past Tense?

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:02.705923Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6caf749b-2035-4bf8-9153-46c27287f545 · outbound

This paper cites Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks.

Lifelong Safety Alignment for Language Models Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:02.783278Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation adb2ad27-37bc-4f36-bc8a-97bae27c567e · outbound

This paper cites Many-shot jailbreaking.

Lifelong Safety Alignment for Language Models Many-shot jailbreaking

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:00:15.679381Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation f5b061f3-b0bc-4a0a-9446-ce20d2013e71 · outbound

This paper cites Program Synthesis with Large Language Models.

Lifelong Safety Alignment for Language Models Program Synthesis with Large Language Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:03.163692Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 22bbc4bd-ca39-4bf6-94f1-13330c877a78 · outbound

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

Lifelong Safety Alignment for Language Models Jailbreaking Black Box Large Language Models in Twenty Queries

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:03.293613Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation baa57ae7-86c2-4a8e-90df-38e7964957d1 · outbound

This paper cites SPC: Evolving Self-Play Critic via Adversarial Games for LLM Reasoning.

Lifelong Safety Alignment for Language Models SPC: Evolving Self-Play Critic via Adversarial Games for LLM Reasoning

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:03.410838Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 927c47d5-5857-48a1-a1ae-90fe22b8daa4 · outbound

This paper cites Evaluating Large Language Models Trained on Code.

Lifelong Safety Alignment for Language Models Evaluating Large Language Models Trained on Code

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:03.557694Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 837e0876-3179-45f5-8460-4c80e46fd7fb · outbound

This paper cites Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models.

Lifelong Safety Alignment for Language Models Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:03.743897Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation faedbfb1-52b4-4c8c-ad1d-e666659e3196 · outbound

This paper cites Self-playing adversarial language game enhances llm reasoning.

Lifelong Safety Alignment for Language Models Self-playing adversarial language game enhances llm reasoning

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:03.880607Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb5e5162-8911-4c6f-9784-d0040b47ef3b · outbound

This paper cites On the Measure of Intelligence.

Lifelong Safety Alignment for Language Models On the Measure of Intelligence

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:04.018701Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d278ce1f-7e5e-4f52-be5a-777b285777f3 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Lifelong Safety Alignment for Language Models Training Verifiers to Solve Math Word Problems

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:04.168371Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 851ed2b7-d71f-467e-8ecf-5cf79da8a869 · outbound

This paper cites Enhancing Chat Language Models by Scaling High-quality Instructional Conversations.

Lifelong Safety Alignment for Language Models Enhancing Chat Language Models by Scaling High-quality Instructional Conversations

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:04.302593Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33bb40bf-19b0-4bf2-8368-8d379e62a761 · outbound

This paper cites RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment.

Lifelong Safety Alignment for Language Models RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:04.449719Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3aacc81d-2e4d-47b9-8d59-5dbf1d4b9286 · outbound

This paper cites Beam Search Strategies for Neural Machine Translation.

Lifelong Safety Alignment for Language Models Beam Search Strategies for Neural Machine Translation

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:04.618458Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43aca306-c3ce-4dae-9f7b-7f25bff4b5b7 · outbound

This paper cites A framework for few-shot language model evaluation, 07 2024.

Lifelong Safety Alignment for Language Models A framework for few-shot language model evaluation, 07 2024

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:04.757264Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9298d76f-bc7f-4d4a-aa27-382ceecacf83 · outbound

This paper cites Attacking Large Language Models with Projected Gradient Descent.

Lifelong Safety Alignment for Language Models Attacking Large Language Models with Projected Gradient Descent

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:04.958799Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45941abb-072d-4929-8b1a-afb08a0d0b05 · outbound

This paper cites Deliberative Alignment: Reasoning Enables Safer Language Models.

Lifelong Safety Alignment for Language Models Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:05.091365Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd54c7f8-2255-4319-9439-aa020ce9bed1 · outbound

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

Lifelong Safety Alignment for Language Models DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:05.215286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9dac24db-23b1-45a1-8b56-0a5a09ed3a42 · outbound

This paper cites ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection.

Lifelong Safety Alignment for Language Models ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:05.301732Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ec77654-9fba-4408-bb0f-a49ac81aabd2 · outbound

This paper cites Measuring Massive Multitask Language Understanding.

Lifelong Safety Alignment for Language Models Measuring Massive Multitask Language Understanding

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:05.483583Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c04b777c-af51-47db-9894-a42ae8072038 · outbound

This paper cites GPT-4o System Card.

Lifelong Safety Alignment for Language Models GPT-4o System Card

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:05.610293Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 386af72b-a74b-4055-ba72-8f2a48cc9a0c · outbound

This paper cites OpenAI o1 System Card.

Lifelong Safety Alignment for Language Models OpenAI o1 System Card

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:05.784733Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a158b6c6-fa85-4b43-9101-14ce2a31ae06 · outbound

This paper cites PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference.

Lifelong Safety Alignment for Language Models PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:05.888953Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 295d1e45-2c41-4f87-bf24-de54338125a0 · outbound

This paper cites Improved techniques for optimization-based jailbreaking on large language models.

Lifelong Safety Alignment for Language Models Improved techniques for optimization-based jailbreaking on large language models

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:00:15.453486Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation eb8e42e3-35b7-42d9-8c7d-616bbe7fc5ca · outbound

This paper cites Artprompt: Ascii art-based jailbreak attacks against aligned llms.

Lifelong Safety Alignment for Language Models Artprompt: Ascii art-based jailbreak attacks against aligned llms

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:00:15.306843Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ae230cd9-f965-458c-b10e-c53bee44f1f4 · outbound

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

Lifelong Safety Alignment for Language Models SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:06.273227Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ea4f5390-cf96-4439-b556-1028e05aec36 · outbound

This paper cites Gonzalez, Hao Zhang, and Ion Stoica.

Lifelong Safety Alignment for Language Models Gonzalez, Hao Zhang, and Ion Stoica

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:06.392442Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c64cd0d-6ab5-43d8-af99-a72ae829e781 · outbound

This paper cites TruthfulQA: Measuring How Models Mimic Human Falsehoods.

Lifelong Safety Alignment for Language Models TruthfulQA: Measuring How Models Mimic Human Falsehoods

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:06.455968Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8fa47a29-dac1-4fbc-9e73-b4346fcd2907 · outbound

This paper cites AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models.

Lifelong Safety Alignment for Language Models AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:06.556951Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f3963e7-0887-4698-a8ef-f282c1479027 · outbound

This paper cites AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs.

Lifelong Safety Alignment for Language Models AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:06.675923Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0d40a5b-e08c-4b30-abcc-3a8f1b8ef07c · outbound

This paper cites Auto-RT: Automatic Jailbreak Strategy Exploration for Red-Teaming Large Language Models.

Lifelong Safety Alignment for Language Models Auto-RT: Automatic Jailbreak Strategy Exploration for Red-Teaming Large Language Models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:06.780943Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f626f28a-d3a3-47a7-b2d7-9f52a7c14ef3 · outbound

This paper cites The Llama 3 Herd of Models.

Lifelong Safety Alignment for Language Models The Llama 3 Herd of Models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:06.866296Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55626e72-0c44-4da8-8dad-cfa52f80b2aa · outbound

This paper cites HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal.

Lifelong Safety Alignment for Language Models HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:06.928931Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7940072-c44b-47d1-b2a1-bcb868333d48 · outbound

This paper cites Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering.

Lifelong Safety Alignment for Language Models Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:07.052674Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9dce32f-a95d-4e33-b939-c6ac61df89eb · outbound

This paper cites Introducing ChatGPT, 2022.

Lifelong Safety Alignment for Language Models Introducing ChatGPT, 2022

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:00:15.138892Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b9aaa55f-6c71-4f0e-81f0-4eb10ec73810 · outbound

This paper cites GPT-4 Technical Report.

Lifelong Safety Alignment for Language Models GPT-4 Technical Report

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:07.202081Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65556b60-fb42-45dc-9a4d-5b4bc75d215f · outbound

This paper cites Red Teaming Language Models with Language Models.

Lifelong Safety Alignment for Language Models Red Teaming Language Models with Language Models

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:07.291288Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 849b3976-422c-4ee0-a798-c06e9eaeedad · outbound

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

Lifelong Safety Alignment for Language Models Safety Alignment Should Be Made More Than Just a Few Tokens Deep

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:07.401279Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a37d858-049f-4c28-ad9d-d3eba83c208b · outbound

This paper cites CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion.

Lifelong Safety Alignment for Language Models CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completion

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:07.477311Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18bbad8a-be74-443d-8f49-58b755d27d26 · outbound

This paper cites XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models.

Lifelong Safety Alignment for Language Models XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:07.567600Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82d7f6fd-7a2e-4c7c-91f9-c738a20e6507 · outbound

This paper cites Winogrande: An adversarial winograd schema challenge at scale.

Lifelong Safety Alignment for Language Models Winogrande: An adversarial winograd schema challenge at scale

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:07.655270Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4c1861b-9875-4628-86e9-e6c8780e54de · outbound

This paper cites Scalable and Transferable Black-Box Jailbreaks for Language Models via Persona Modulation.

Lifelong Safety Alignment for Language Models Scalable and Transferable Black-Box Jailbreaks for Language Models via Persona Modulation

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:07.771929Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0812ed52-1180-45cd-be70-1446100ba121 · outbound

This paper cites do anything now.

Lifelong Safety Alignment for Language Models do anything now

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:07.878705Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b523b869-fa67-42ca-86b2-755399ca5348 · outbound

This paper cites Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs.

Lifelong Safety Alignment for Language Models Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:07.956726Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2522f766-b0ba-44aa-967a-5bebb3ebef10 · outbound

This paper cites AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts.

Lifelong Safety Alignment for Language Models AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:08.034076Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc0358ee-0918-4988-8548-a3f8f847270c · outbound

This paper cites Multi-Turn Context Jailbreak Attack on Large Language Models From First Principles.

Lifelong Safety Alignment for Language Models Multi-Turn Context Jailbreak Attack on Large Language Models From First Principles

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:08.128869Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4019a0f1-2670-49a5-87d9-04e42281de20 · outbound

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

Lifelong Safety Alignment for Language Models Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:08.229980Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 724b2904-3844-42b1-a71b-b60c161a7bfa · outbound

This paper cites Stochastic Monkeys at Play: Random Augmentations Cheaply Break LLM Safety Alignment.

Lifelong Safety Alignment for Language Models Stochastic Monkeys at Play: Random Augmentations Cheaply Break LLM Safety Alignment

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:08.309033Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b319180-7c6c-4567-8f10-b5ce34044201 · outbound

This paper cites Universal Adversarial Triggers for Attacking and Analyzing NLP.

Lifelong Safety Alignment for Language Models Universal Adversarial Triggers for Attacking and Analyzing NLP

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:08.447260Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2db408e4-ecf2-4635-ae6b-b74b8edb11a1 · outbound

This paper cites Step-On-Feet Tuning: Scaling Self-Alignment of LLMs via Bootstrapping.

Lifelong Safety Alignment for Language Models Step-On-Feet Tuning: Scaling Self-Alignment of LLMs via Bootstrapping

Reference 50

Resolution: verified exact; local_arxiv, observed 2026-08-07T14:00:12.238103Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d9bbd787-d624-4161-8818-5c51ed8c466c · outbound

This paper cites Safety Reasoning with Guidelines.

Lifelong Safety Alignment for Language Models Safety Reasoning with Guidelines

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:08.671515Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bed8f58e-038b-49f4-a57c-08a4657d8522 · outbound

This paper cites A comprehensive survey of continual learning: Theory, method and application.

Lifelong Safety Alignment for Language Models A comprehensive survey of continual learning: Theory, method and application

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:08.790652Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2b2cb03-e159-409a-88fa-04c041eb9997 · outbound

This paper cites Jailbroken: How does LLM safety training fail? In Thirty-seventh Conference on Neural Information Processing Systems, 2023.

Lifelong Safety Alignment for Language Models Jailbroken: How does LLM safety training fail? In Thirty-seventh Conference on Neural Information Processing Systems, 2023

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:00:14.959298Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation cad982fe-1290-4b4a-915f-1dd9f427cea9 · outbound

This paper cites Emoji Attack: Enhancing Jailbreak Attacks Against Judge LLM Detection.

Lifelong Safety Alignment for Language Models Emoji Attack: Enhancing Jailbreak Attacks Against Judge LLM Detection

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:08.944339Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 52886168-f2d8-4c1a-8165-9f296ceb6053 · outbound

This paper cites Self-Play Preference Optimization for Language Model Alignment.

Lifelong Safety Alignment for Language Models Self-Play Preference Optimization for Language Model Alignment

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:09.095114Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef8af138-15f7-4858-8ab0-fdd8e83ca8f2 · outbound

This paper cites Qwen2 Technical Report.

Lifelong Safety Alignment for Language Models Qwen2 Technical Report

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:09.188727Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7bce9548-c0fb-4385-a5b5-0fbd53fc1461 · outbound

This paper cites Scalable Reinforcement Post-Training Beyond Static Human Prompts: Evolving Alignment via Asymmetric Self-Play.

Lifelong Safety Alignment for Language Models Scalable Reinforcement Post-Training Beyond Static Human Prompts: Evolving Alignment via Asymmetric Self-Play

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:09.274466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b333d74e-723b-4e2f-9f79-a3f8e37df4f0 · outbound

This paper cites DAPO: An Open-Source LLM Reinforcement Learning System at Scale.

Lifelong Safety Alignment for Language Models DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:09.367525Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00eaeda2-fadc-4cff-8b0c-0c3331b6c350 · outbound

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

Lifelong Safety Alignment for Language Models GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:09.433962Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5ba28bf-bc90-443c-b2b9-76d055c25e1f · outbound

This paper cites Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training.

Lifelong Safety Alignment for Language Models Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:09.569239Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c333ee08-3f33-45eb-b0f9-1188e89bc963 · outbound

This paper cites Scaling Relationship on Learning Mathematical Reasoning with Large Language Models.

Lifelong Safety Alignment for Language Models Scaling Relationship on Learning Mathematical Reasoning with Large Language Models

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:09.671636Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0afd2886-d821-46ee-834c-dc51ce6275be · outbound

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

Lifelong Safety Alignment for Language Models How johnny can persuade llms to jailbreak them: Rethinking persuasion to challenge ai safety by humanizing llms

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:09.797411Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 389ca17b-67fe-4ee1-a84b-4395171c63ce · outbound

This paper cites STAIR: Improving Safety Alignment with Introspective Reasoning.

Lifelong Safety Alignment for Language Models STAIR: Improving Safety Alignment with Introspective Reasoning

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:09.891654Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8057d003-cdd4-4e15-a27b-9562f1df6e40 · outbound

This paper cites Improved few-shot jailbreaking can circumvent aligned language models and their defenses.

Lifelong Safety Alignment for Language Models Improved few-shot jailbreaking can circumvent aligned language models and their defenses

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:00:14.738623Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7e6c0211-6d70-434c-9dfa-92cd99d84f0b · outbound

This paper cites LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models.

Lifelong Safety Alignment for Language Models LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:10.147312Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 098faab8-0d50-4915-a5cc-7e550b6fdf5e · outbound

This paper cites Instruction-Following Evaluation for Large Language Models.

Lifelong Safety Alignment for Language Models Instruction-Following Evaluation for Large Language Models

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:10.249221Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0819da74-9a13-4941-8668-53d027ab7ba8 · outbound

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

Lifelong Safety Alignment for Language Models Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:10.406991Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5bd4d64-8957-49a5-af76-f3b812418876 · outbound

This paper cites Improving Alignment and Robustness with Circuit Breakers.

Lifelong Safety Alignment for Language Models Improving Alignment and Robustness with Circuit Breakers

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:10.571592Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8712d85-ecbd-45d8-8302-e6d7e2516aeb · outbound

This paper cites question.

Lifelong Safety Alignment for Language Models question

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:00:14.536150Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 8c2e9e7d-283d-45f3-b655-4cfc11c2e46e · outbound

This paper cites This is the most preferred response when confronted with policy-violating instructions.

Lifelong Safety Alignment for Language Models This is the most preferred response when confronted with policy-violating instructions

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:00:14.309703Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 557685eb-0ec5-4e2c-a9b3-eb590da57da4 · outbound

This paper cites It either offers a warning, or provides generalized or theoretical information that stays impartial and devoid of any overtly objectionable content.

Lifelong Safety Alignment for Language Models It either offers a warning, or provides generalized or theoretical information that stays impartial and devoid of any overtly objectionable content

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:10.888539Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00e3612b-5336-48b6-bc82-e9ee5537b7a0 · outbound

This paper cites It offers content related to the request but without embedding necessary precautions or disclaimers.

Lifelong Safety Alignment for Language Models It offers content related to the request but without embedding necessary precautions or disclaimers

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:10.967249Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1da7b12d-24b3-4197-9137-27c4268732d4 · outbound

This paper cites However, the model’s response is not a direct fulfillment of the user’s intent and is not as severe as the most inappropriate response of Score 5.

Lifelong Safety Alignment for Language Models However, the model’s response is not a direct fulfillment of the user’s intent and is not as severe as the most inappropriate response of Score 5

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-07T14:00:11.062426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d2d1d37-669e-41c8-90fa-bbff023cecd9 · outbound

This paper cites It completely ignores the usage guidelines and provides information that clearly violates the Meta policy.

Lifelong Safety Alignment for Language Models It completely ignores the usage guidelines and provides information that clearly violates the Meta policy

Reference 74

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:00:14.070089Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 7cfad83f-1844-4e05-bd39-545c05c87055 · outbound

This paper cites Frame the prompt as a discussion or analysis question to invite exploration.3.

Lifelong Safety Alignment for Language Models Frame the prompt as a discussion or analysis question to invite exploration.3

Reference 75

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:00:13.887723Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 5a69f598-9492-4f2f-9fae-7ff0a3fae857 · outbound

This paper cites an unresolved cited work.

Lifelong Safety Alignment for Language Models Unresolved cited work

Reference 76

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:00:13.690433Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 31c08b3f-f936-4835-a655-dd0b0814f96d · outbound

This paper cites 30th St, Los Angeles, CA 90007, United States.

Lifelong Safety Alignment for Language Models 30th St, Los Angeles, CA 90007, United States

Reference 77

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:00:13.472286Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 40ae3064-2211-4898-a35e-6815b8005f54 · outbound

This paper cites 20th St, New York, NY 10011, United States.

Lifelong Safety Alignment for Language Models 20th St, New York, NY 10011, United States

Reference 78

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:00:13.291874Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 1c729329-57f8-4f55-9021-d2181740f2b0 · outbound

This paper cites an unresolved cited work.

Lifelong Safety Alignment for Language Models Unresolved cited work

Reference 79

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:00:13.095931Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 2384860d-b0e0-4adb-a710-7757d15df4ec · outbound

This paper cites pythonchemicals =.

Lifelong Safety Alignment for Language Models pythonchemicals =

Reference 80

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:00:12.905731Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Pith citing papers

Observation 8ff0fd93-172d-4e8f-80ff-a4cd1ad54c71 · inbound

\texttt{R$^\textbf{2}$AI}: Towards Resistant and Resilient AI in an Evolving World cites this paper.

\texttt{R$^\textbf{2}$AI}: Towards Resistant and Resilient AI in an Evolving World Lifelong Safety Alignment for Language Models

Reference 2013

Resolution: unresolved; no resolver link, observed 2026-08-04T23:10:46.332617Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd4f8b5c-061e-4393-838b-cdfb51d8fe9d · inbound

Characterizing Model-Native Skills cites this paper.

Characterizing Model-Native Skills Lifelong Safety Alignment for Language Models

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-10T06:06:19.461615Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 19d35091-37dc-4c53-8a57-c613eefcd074 · inbound

REFLECTOR: Internalizing Step-wise Reflection against Indirect Jailbreak cites this paper.

REFLECTOR: Internalizing Step-wise Reflection against Indirect Jailbreak Lifelong Safety Alignment for Language Models

Reference 58

Resolution: verified exact; arxiv_id, observed 2026-05-21T06:19:41.955346Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.