Paper Citation Record · LEDGER

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning

As of 9 August 2026, this Paper Citation Record lists 54 of 54 outbound references and 3 inbound Pith citation observations for arXiv:2507.14987.

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

pith.paper-citation-record.v1
2507.14987 v1

Coverage vector

measured 54 of 54 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T15:48:01.488303Z

measured 57 of 57 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-05T23:46:20.547519Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T19:40:06.671432Z

Reference resolution

54 of 54 outbound references displayed

verified exact0
verified fuzzy20
unresolved34
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 88ba8c8e-c977-4d46-b786-55e5cba25ab7 · outbound

This paper cites Claude 3.5 sonnet model card addendum.

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning Claude 3.5 sonnet model card addendum

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:48:02.229668Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation d80e5d73-1e38-4a03-81a6-2d3663420e85 · outbound

This paper cites Claude 3.7 sonnet system card.

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning Claude 3.7 sonnet system card

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:48:02.219762Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 0bd55893-82c6-4e7f-b58f-c7a20b20f6f0 · outbound

This paper cites Gemma 2: Improving Open Language Models at a Practical Size.

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning Gemma 2: Improving Open Language Models at a Practical Size

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-06T15:48:01.309058Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3fe5fa3a-47f8-40a7-a1fb-c09fc21ac8d2 · outbound

This paper cites Qwen2.5 Technical Report.

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning Qwen2.5 Technical Report

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T15:48:01.312914Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7dbd5c6-5592-49c6-ab0c-908c54cd6b8a · outbound

This paper cites DeepSeek-V3 Technical Report.

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning DeepSeek-V3 Technical Report

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T15:48:01.316811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3169a0e9-52a7-4e5f-812e-830775b113a0 · outbound

This paper cites Hadi Amini, and Yanzhao Wu.

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning Hadi Amini, and Yanzhao Wu

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:48:02.209551Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation e6826717-384c-4b13-b4d2-b0eedd7eb3d9 · outbound

This paper cites Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment.

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T15:48:01.323942Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c4445efa-845a-47c7-91c3-2a9bb63aef44 · outbound

This paper cites Safe + Safe = Unsafe? Exploring How Safe Images Can Be Exploited to Jailbreak Large Vision-Language Models.

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning Safe + Safe = Unsafe? Exploring How Safe Images Can Be Exploited to Jailbreak Large Vision-Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T15:48:01.327760Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ce16309-30d6-4c2e-81ab-dbe6b378be84 · outbound

This paper cites Kummerfeld, and Rada Mihalcea.

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning Kummerfeld, and Rada Mihalcea

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:48:02.198848Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 9e2ec079-d332-444a-9c5b-7f9aabb0ce09 · outbound

This paper cites Towards understanding jailbreak attacks in llms: A representation space analysis.

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning Towards understanding jailbreak attacks in llms: A representation space analysis

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:48:02.187307Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ae7756c7-859a-47ee-9ec7-d1d2f800487f · outbound

This paper cites Uncovering safety risks of large language models through concept activation vector.

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning Uncovering safety risks of large language models through concept activation vector

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:48:02.176509Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation b86170f1-ddd6-431b-80c1-1690a8b0d795 · outbound

This paper cites On prompt-driven safeguarding for large language models.

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning On prompt-driven safeguarding for large language models

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:48:02.164319Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation f572c8e5-e434-4ba6-bbb2-951b37b78fb2 · outbound

This paper cites Nguyen, Jun Sun, and Tat - Seng Chua.

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning Nguyen, Jun Sun, and Tat - Seng Chua

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:48:02.154293Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 337aa62b-04b5-42e8-a50f-5fb9a4304c0a · outbound

This paper cites Jailbroken: How does LLM safety training fail? In NeurIPS, 2023.

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning Jailbroken: How does LLM safety training fail? In NeurIPS, 2023

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:48:02.143935Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 0064e74f-d67b-4e40-b717-2c99ddc7614c · outbound

This paper cites Safety Reasoning with Guidelines.

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning Safety Reasoning with Guidelines

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T15:48:01.356987Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03d9e388-4c7d-45ee-9429-c8443e144e39 · outbound

This paper cites Rule based rewards for language model safety.

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning Rule based rewards for language model safety

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:48:02.132567Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 1865f620-a909-40b7-a460-e45446f6d8f0 · outbound

This paper cites Safety is not only about refusal: Reasoning-enhanced fine-tuning for interpretable LLM safety.

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning Safety is not only about refusal: Reasoning-enhanced fine-tuning for interpretable LLM safety

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-06T15:48:01.363452Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a6aa999a-65fe-4a16-a1af-f85c3a9b6d6d · outbound

This paper cites Zhao, Kelvin Guu, Adams Wei Yu, Brian Lester, Nan Du, Andrew M.

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning Zhao, Kelvin Guu, Adams Wei Yu, Brian Lester, Nan Du, Andrew M

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:48:02.121098Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 808083e7-b3a3-4e0c-ae05-a92ca6e7c8ac · outbound

This paper cites an unresolved cited work.

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning Unresolved cited work

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T15:48:01.369990Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 259e10b5-eb2d-4174-be50-c6a1a9969e59 · outbound

This paper cites Manning, Stefano Ermon, and Chelsea Finn.

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning Manning, Stefano Ermon, and Chelsea Finn

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T15:48:01.373404Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b502d8ad-ff9b-4891-9fb4-fa4f7923d7b2 · outbound

This paper cites Safe lora: The silver lining of reducing safety risks when finetuning large language models.

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning Safe lora: The silver lining of reducing safety risks when finetuning large language models

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:48:02.095789Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation c8dd559e-859e-45f9-8052-95d8bd935554 · outbound

This paper cites Zico Kolter, Matt Fredrikson, and Dan Hendrycks.

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning Zico Kolter, Matt Fredrikson, and Dan Hendrycks

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:48:02.085637Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation c4b5728f-b8ff-4436-83de-53d40cfe133f · outbound

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

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning Safety Alignment Should Be Made More Than Just a Few Tokens Deep

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T15:48:01.382809Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 449e52f3-1076-4415-b5b0-64a3b80315c0 · outbound

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

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T15:48:01.386002Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1600e39f-f572-4f6c-a4ea-866b9f0be95d · outbound

This paper cites Enhancing model defense against jailbreaks with proactive safety reasoning.

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning Enhancing model defense against jailbreaks with proactive safety reasoning

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T15:48:01.388982Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c04d912f-6ad0-46de-9970-157ed05c112d · outbound

This paper cites Reasoning-to-defend: Safety-aware reasoning can defend large language models from jailbreaking.

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning Reasoning-to-defend: Safety-aware reasoning can defend large language models from jailbreaking

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T15:48:01.392182Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c62134f-a5b8-4b75-8a62-20223ca065e8 · outbound

This paper cites Bikel, Jason E.

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning Bikel, Jason E

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:48:02.076369Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation d50ed610-393a-461e-9e5c-49de9b04a66c · outbound

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

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning Does Refusal Training in LLMs Generalize to the Past Tense?

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-06T15:48:01.398901Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b78b9f0-7a0e-4039-8e93-d406d8f2ae0c · outbound

This paper cites Fine-tuning aligned language models compromises safety, even when users do not intend to! In ICLR , 2024 b.

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning Fine-tuning aligned language models compromises safety, even when users do not intend to! In ICLR , 2024 b

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:48:02.066996Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation f1929073-70ea-4d28-aba7-49977dfbb656 · outbound

This paper cites Constitutional AI: Harmlessness from AI Feedback.

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning Constitutional AI: Harmlessness from AI Feedback

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-06T15:48:01.405908Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 899225ce-cc30-48db-baea-f4a0d0aee895 · outbound

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

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-06T15:48:01.409511Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 360512d6-0b7c-4d22-9ad5-1df3e4542611 · outbound

This paper cites Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model.

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-06T15:48:01.413147Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81b675cb-451b-41e5-8199-e56ff022df83 · outbound

This paper cites Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?.

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-06T15:48:01.416557Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2109089-99c2-41ee-9788-e561901be489 · outbound

This paper cites Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs.

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRs

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-06T15:48:01.420708Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9af60e70-f02b-4ebb-8450-da15badc50b0 · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-06T15:48:01.424241Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a80a100-a6ef-4799-9694-013717548600 · outbound

This paper cites Proximal Policy Optimization Algorithms.

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning Proximal Policy Optimization Algorithms

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-06T15:48:01.428077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5ed7fa2-05ae-42b8-83bd-5e6dc2241560 · outbound

This paper cites Kimi k1.5: Scaling Reinforcement Learning with LLMs.

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning Kimi k1.5: Scaling Reinforcement Learning with LLMs

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-06T15:48:01.431316Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6d57317-baef-4e62-ac3f-bf8c51e592c0 · outbound

This paper cites Jordan, and Pieter Abbeel.

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning Jordan, and Pieter Abbeel

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:48:02.056797Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 0f6e7206-c031-46f3-8e11-5fbed43cc04d · outbound

This paper cites A strongreject for empty jailbreaks.

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning A strongreject for empty jailbreaks

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-06T15:48:01.437956Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05a11772-9b8d-4347-87ad-2ea278f2011e · outbound

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

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-06T15:48:01.441397Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cda7c6b2-92cc-4789-890d-0239ae4548ac · outbound

This paper cites Wildguard: Open one-stop moderation tools for safety risks, jailbreaks, and refusals of llms.

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning Wildguard: Open one-stop moderation tools for safety risks, jailbreaks, and refusals of llms

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:48:02.040032Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 04cb8820-72d2-4536-b12f-2c765052765e · outbound

This paper cites an unresolved cited work.

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning Unresolved cited work

Reference 43

Resolution: unresolved; raw_fallback, observed 2026-08-06T15:48:02.029712Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 53376565-e138-4c82-bfd6-a4b69299a99a · outbound

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

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning Jailbreaking Black Box Large Language Models in Twenty Queries

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-06T15:48:01.451746Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2de32363-6a72-45f3-a94f-7fa96500ef52 · outbound

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

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-06T15:48:01.454863Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ddb9a189-4774-4efc-af9c-4a844b2ae6c8 · outbound

This paper cites Smith, Yejin Choi, and Hanna Hajishirzi.

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning Smith, Yejin Choi, and Hanna Hajishirzi

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:48:02.019937Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 6a0dec33-4c25-4381-903b-8a2bfec30c1e · outbound

This paper cites Measuring massive multitask language understanding.

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning Measuring massive multitask language understanding

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:48:02.009395Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 9d460353-3ff9-41c4-b0c3-679149ea8655 · outbound

This paper cites Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators.

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-06T15:48:01.464564Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95f9e80f-c966-49b4-9e9e-1dc38a4d5fe4 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning Training Verifiers to Solve Math Word Problems

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-06T15:48:01.467912Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ffa41b95-17d9-4168-811e-97642a8be57d · outbound

This paper cites The Llama 3 Herd of Models.

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning The Llama 3 Herd of Models

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-06T15:48:01.471447Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9b04422-6b54-44f1-9b15-d7d196de2a5f · outbound

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

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-06T15:48:01.475049Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 572296ea-4dd0-4882-9ef0-3338dad7fd00 · outbound

This paper cites Free dolly: Introducing the world's first truly open instruction-tuned llm, 2023.

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning Free dolly: Introducing the world's first truly open instruction-tuned llm, 2023

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-06T15:48:01.478311Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7feb1d53-edbb-42e0-9f61-9bff21590fc5 · outbound

This paper cites Xstest: A test suite for identifying exaggerated safety behaviours in large language models.

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning Xstest: A test suite for identifying exaggerated safety behaviours in large language models

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T15:48:01.991310Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 22bfb320-4556-4c0c-8a4a-51cafd65d2cc · outbound

This paper cites HybridFlow: A Flexible and Efficient RLHF Framework.

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning HybridFlow: A Flexible and Efficient RLHF Framework

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-06T15:48:01.484886Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c2cfbf5-5502-4743-bb2f-114e7d7fc1a7 · outbound

This paper cites Iterative preference learning from human feedback: Bridging theory and practice for rlhf under kl-constraint, 2024.

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning Iterative preference learning from human feedback: Bridging theory and practice for rlhf under kl-constraint, 2024

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-06T15:48:01.488303Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 0ad39314-b1f0-485a-8b5f-70fe4ef8b5c0 · inbound

Self-ReSET: Learning to Self-Recover from Unsafe Reasoning Trajectories cites this paper.

Self-ReSET: Learning to Self-Recover from Unsafe Reasoning Trajectories AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning

Reference 33

Resolution: verified exact; arxiv_id, observed 2026-05-12T02:11:16.129970Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation a1575c0b-db97-42d4-a424-7ccff2530cb6 · inbound

PolicyAlign: Direct Policy-Based Safety Alignment for Large Language Models cites this paper.

PolicyAlign: Direct Policy-Based Safety Alignment for Large Language Models AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning

Reference 41

Resolution: metadata mismatch; arxiv_id, observed 2026-07-04T19:40:06.672952Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 83c5b1b7-a17d-416c-9347-9ab31cd1660e · inbound

When Refusal Looks Safe: The Refusal-Cue Shortcut in Safety Guard Models cites this paper.

When Refusal Looks Safe: The Refusal-Cue Shortcut in Safety Guard Models AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-05T23:46:20.547519Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.