Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models | Paper Citation Record

Observation e535d23d-1b51-4d28-9edc-b78565171639 · outbound

This paper cites Claude’s character.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models Claude’s character

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2007a67a-3aff-49b3-8c50-40eb67c6fe44 · outbound

This paper cites Many-shot jailbreaking, 2024.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models Many-shot jailbreaking, 2024

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation adc23781-602a-480a-a51c-177101e819a9 · outbound

This paper cites A General Language Assistant as a Laboratory for Alignment.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models A General Language Assistant as a Laboratory for Alignment

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fff01f54-f879-4929-8129-bd388b3cce0a · outbound

This paper cites Program Synthesis with Large Language Models.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models Program Synthesis with Large Language Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 956d5974-4d01-4b86-8521-a52a591b9480 · outbound

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

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback

Reference 5

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92681e02-0040-40c5-a795-b16676b54330 · outbound

This paper cites Constitutional AI: Harmlessness from AI Feedback.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models Constitutional AI: Harmlessness from AI Feedback

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2010cc08-779b-42dc-9d27-ba7c748b0adb · outbound

This paper cites LongAlign: A recipe for long context alignment of large language models.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models LongAlign: A recipe for long context alignment of large language models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d10051fe-6d6b-4033-9b9c-152db38711d8 · outbound

This paper cites Curriculum learning.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models Curriculum learning

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0fc06c03-7f69-4ed8-81c6-a4277db69c78 · outbound

This paper cites Evaluating Large Language Models Trained on Code.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models Evaluating Large Language Models Trained on Code

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d876017-4794-45ed-855b-4968ff9f0d85 · outbound

This paper cites Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83c975b1-9a08-4524-9236-6867b31e8f00 · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models Training Verifiers to Solve Math Word Problems

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46ae21ea-162d-4942-bf7f-c427d8643f01 · outbound

This paper cites Opencompass: A universal evaluation platform for foundation models.https://github.com/open-compass/opencompass, 2023.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models Opencompass: A universal evaluation platform for foundation models.https://github.com/open-compass/opencompass, 2023

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e38864ee-f388-4a0a-aa82-5b526ea05500 · outbound

This paper cites Safe rlhf: Safe reinforcement learning from human feedback.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models Safe rlhf: Safe reinforcement learning from human feedback

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a87e9002-66b7-4394-aeca-2f0bc339054d · outbound

This paper cites Oyster-i: Beyond refusal–constructive safety alignment for responsible language models.arXiv preprint arXiv:2509.01909, 2025.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models Oyster-i: Beyond refusal–constructive safety alignment for responsible language models.arXiv preprint arXiv:2509.01909, 2025

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5e4fe43-fcb3-435c-9fa4-0ad75df5166e · outbound

This paper cites Control illusion: The failure of instruction hierarchies in large language models.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models Control illusion: The failure of instruction hierarchies in large language models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46dd93e9-8734-44cb-884f-fca6e47eacd3 · outbound

This paper cites On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models On the Sensitivity of Instruction-tuned LLMs to Harmful Sentences in Long Inputs

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25543999-5450-48e0-aea7-94063d035d8e · outbound

This paper cites Not what you’ve signed up for: Compromising real-world llm-integrated applications with indirect prompt injection.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models Not what you’ve signed up for: Compromising real-world llm-integrated applications with indirect prompt injection

Reference 17

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9561dc8-97ce-42f3-af4f-499781103678 · outbound

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

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20305956-1b4b-4a27-a87e-0e1310e0bd50 · outbound

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

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 19

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05877839-d1bc-4016-9623-4574e03fa251 · outbound

This paper cites Chinese SimpleQA: A Chinese Factuality Evaluation for Large Language Models.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models Chinese SimpleQA: A Chinese Factuality Evaluation for Large Language Models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59620ea2-e739-469c-a4be-c471bfebb2ec · outbound

This paper cites Measuring massive multitask language understanding.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models Measuring massive multitask language understanding

Reference 21

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8fa37684-2268-4b7d-a9a4-3cb189129a27 · outbound

This paper cites Measuring mathematical problem solving with the MATH dataset.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models Measuring mathematical problem solving with the MATH dataset

Reference 22

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation df678c38-2239-4c77-ab04-162482503552 · outbound

This paper cites Orpo: Monolithic preference optimization without reference model.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models Orpo: Monolithic preference optimization without reference model

Reference 23

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0041bd1b-07d1-4fec-9b90-014fd56b45db · outbound

This paper cites LongSafety: Enhance Safety for Long-Context LLMs.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models LongSafety: Enhance Safety for Long-Context LLMs

Reference 24

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 351f30d8-1e0d-4c8b-90d8-e0d13e62d2f1 · outbound

This paper cites C-eval: A multi-level multi-discipline chinese evaluation suite for foundation models.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models C-eval: A multi-level multi-discipline chinese evaluation suite for foundation models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6bc31ac-bef5-4dc2-ac76-1eb8b1227917 · outbound

This paper cites Safe rlhf-v: Safe reinforcement learning from multi-modal human feedback.Advances in Neural Information Processing Systems, 38:46146–46182, 2026.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models Safe rlhf-v: Safe reinforcement learning from multi-modal human feedback.Advances in Neural Information Processing Systems, 38:46146–46182, 2026

Reference 26

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5904b95-1418-4050-a09e-f97e90b07747 · outbound

This paper cites Safedpo: A simple approach to direct preference optimization with enhanced safety.arXiv preprint arXiv:2505.20065, 2025.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models Safedpo: A simple approach to direct preference optimization with enhanced safety.arXiv preprint arXiv:2505.20065, 2025

Reference 27

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c642110c-73e6-43fb-bb93-10de93329cf6 · outbound

This paper cites On information and sufficiency.The Annals of Mathematical Statistics, 22(1):79–86, 1951.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models On information and sufficiency.The Annals of Mathematical Statistics, 22(1):79–86, 1951

Reference 28

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40b2fb8f-091c-43d6-a0bf-4311aa8704ff · outbound

This paper cites RACE: Large-scale ReAding comprehension dataset from examinations.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models RACE: Large-scale ReAding comprehension dataset from examinations

Reference 29

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26c46d4f-3fe4-4dc3-9300-c934de21b718 · outbound

This paper cites Tulu 3: Pushing Frontiers in Open Language Model Post-Training.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models Tulu 3: Pushing Frontiers in Open Language Model Post-Training

Reference 30

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d2c26e3-56f4-4d00-b0a7-8be9a38a0f60 · outbound

This paper cites Binary codes capable of correcting deletions, insertions, and reversals.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models Binary codes capable of correcting deletions, insertions, and reversals

Reference 31

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ffdca804-bfa7-470a-a1da-f10440d7357d · outbound

This paper cites Model Spec Midtraining: Improving How Alignment Training Generalizes.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models Model Spec Midtraining: Improving How Alignment Training Generalizes

Reference 32

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a68cbc75-08f5-4c87-ae0c-862b4c087a02 · outbound

This paper cites Optimizing Safe and Aligned Language Generation: A Multi-Objective GRPO Approach.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models Optimizing Safe and Aligned Language Generation: A Multi-Objective GRPO Approach

Reference 33

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32fa5b9c-35c5-4639-bdfe-74eacf96227e · outbound

This paper cites Let's Verify Step by Step.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models Let's Verify Step by Step

Reference 34

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08085187-6615-47ac-92e7-9c4eb0cc7b4e · outbound

This paper cites TruthfulQA: Measuring how models mimic human falsehoods.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models TruthfulQA: Measuring how models mimic human falsehoods

Reference 35

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c30963ce-27fa-400e-a435-fb9881c66479 · outbound

This paper cites Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation

Reference 36

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cdf2d924-e667-4355-9bee-0eb43b158dd3 · outbound

This paper cites Longsafety: Evaluating long-context safety of large language models.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models Longsafety: Evaluating long-context safety of large language models

Reference 37

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60e21baf-57a4-4d77-b1f7-139ae4d6bfe7 · outbound

This paper cites an unresolved cited work.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models Unresolved cited work

Reference 38

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f30fb6fa-0919-48cb-8e64-fee704893336 · outbound

This paper cites Can a suit of armor conduct electricity? a new dataset for open book question answering.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models Can a suit of armor conduct electricity? a new dataset for open book question answering

Reference 39

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 598d99f4-ed63-4883-90eb-3ba4a36a2daf · outbound

This paper cites SaRO: Enhancing LLM Safety through Reasoning-based Alignment.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models SaRO: Enhancing LLM Safety through Reasoning-based Alignment

Reference 40

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12118996-c048-4b4c-9136-7bccb8827f3c · outbound

This paper cites The model spec, 2024.https://model-spec.openai.com/.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models The model spec, 2024.https://model-spec.openai.com/

Reference 41

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45bf8c17-ba32-4f6b-a7ad-5629bd9cea14 · outbound

This paper cites Training language models to follow instructions with human feedback.Advances in neural information processing systems, 35:27730–27744, 2022.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models Training language models to follow instructions with human feedback.Advances in neural information processing systems, 35:27730–27744, 2022

Reference 42

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c55ea4a-60c2-4f07-a6f5-3b82f3319bda · outbound

This paper cites Humanity's Last Exam.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models Humanity's Last Exam

Reference 43

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c75e7126-3b2a-4c8e-a077-9a0f7510f204 · outbound

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

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models Direct preference optimization: Your language model is secretly a reward model

Reference 44

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7bc08d9e-aed8-44a2-9db2-d7e210a79c52 · outbound

This paper cites GPQA: A Graduate-Level Google-Proof Q&A Benchmark.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models GPQA: A Graduate-Level Google-Proof Q&A Benchmark

Reference 45

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c43be9f-b268-4306-add3-48da0bc2548f · outbound

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

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models Xstest: A test suite for identifying exaggerated safety behaviours in large language models

Reference 46

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91cf2f12-65f6-43ca-bd0d-e83599290789 · outbound

This paper cites Ignore this title and hackaprompt: Exposing systemic vulnerabilities of llms through a global prompt hacking competition.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models Ignore this title and hackaprompt: Exposing systemic vulnerabilities of llms through a global prompt hacking competition

Reference 47

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 732851c2-45a6-41ac-9310-5f615cf997b8 · outbound

This paper cites thefuzz: Fuzzy string matching in Python, 2024.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models thefuzz: Fuzzy string matching in Python, 2024

Reference 48

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21fbbfe8-de3d-4c63-8f8d-10fa6c74c663 · outbound

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

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 49

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bec311c1-c363-4b0d-892d-0ce7683f1d4a · outbound

This paper cites OpenAI GPT-5 System Card.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models OpenAI GPT-5 System Card

Reference 50

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 914e1bc7-9d23-4e8f-8610-9eb17f60e148 · outbound

This paper cites A strongreject for empty jailbreaks.Advances in Neural Information Processing Systems, 37:125416–125440, 2024.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models A strongreject for empty jailbreaks.Advances in Neural Information Processing Systems, 37:125416–125440, 2024

Reference 51

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70561fcc-fc23-44d7-addf-12c6f7ec59bb · outbound

This paper cites DetectLLM: Leveraging log rank information for zero-shot detection of machine-generated text.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models DetectLLM: Leveraging log rank information for zero-shot detection of machine-generated text

Reference 52

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 970484f5-383a-4824-85f1-4ef402ab00dd · outbound

This paper cites Investigating prior knowledge for challenging chinese machine reading comprehension.Transactions of the Association for Computational Linguistics (TACL), 8:141–155, 2020.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models Investigating prior knowledge for challenging chinese machine reading comprehension.Transactions of the Association for Computational Linguistics (TACL), 8:141–155, 2020

Reference 53

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff825f88-ba4b-4b42-9901-7f4333f48658 · outbound

This paper cites Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them

Reference 54

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9cf904e1-8fb2-4068-affc-a4aebf5fb687 · outbound

This paper cites Commonsenseqa: A question answering challenge targeting commonsense knowledge.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models Commonsenseqa: A question answering challenge targeting commonsense knowledge

Reference 55

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 570ba94a-418c-4fbd-855e-f0f0a14f1219 · outbound

This paper cites The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions

Reference 56

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8acc3b5f-2cb8-40c7-8656-0163e660db50 · outbound

This paper cites Mmlu-pro: A more robust and challenging multi-task language understanding benchmark.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models Mmlu-pro: A more robust and challenging multi-task language understanding benchmark

Reference 57

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0aec7b8-62f8-47a6-8f2c-66861ccc1e58 · outbound

This paper cites Do-not-answer: Evaluating safeguards in llms.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models Do-not-answer: Evaluating safeguards in llms

Reference 58

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56412ce6-3979-4eab-acb3-6b5f74eb09f5 · outbound

This paper cites Measuring short-form factuality in large language models.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models Measuring short-form factuality in large language models

Reference 59

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ec93d36-b4e4-46de-bef3-b6f996c02f22 · outbound

This paper cites Benchmarking and defending against indirect prompt injection attacks on large language models.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models Benchmarking and defending against indirect prompt injection attacks on large language models

Reference 60

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 455e3c51-0bb8-470d-860c-338d8e6cf62f · outbound

This paper cites S-eval: Towards automated and comprehensive safety evaluation for large language models.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models S-eval: Towards automated and comprehensive safety evaluation for large language models

Reference 61

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13e43977-b44e-4383-bfa6-66195151621c · outbound

This paper cites From Hard Refusals to Safe-Completions: Toward Output-Centric Safety Training.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models From Hard Refusals to Safe-Completions: Toward Output-Centric Safety Training

Reference 62

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d41dde8-4754-40d9-b1f4-f6ffb33c94e8 · outbound

This paper cites Many-Tier Instruction Hierarchy in LLM Agents.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models Many-Tier Instruction Hierarchy in LLM Agents

Reference 63

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59814d93-a853-4900-ad16-902cc5ea06c8 · outbound

This paper cites Iheval: Evaluating language models on following the instruction hierarchy.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models Iheval: Evaluating language models on following the instruction hierarchy

Reference 64

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d90b5afb-acf4-4693-8e39-7cc9bbff10d8 · outbound

This paper cites Wildchat: 1m chatgpt interaction logs in the wild.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models Wildchat: 1m chatgpt interaction logs in the wild

Reference 65

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ccb6437-a238-4d30-be10-296192e4cb1a · outbound

This paper cites Improving llm safety alignment with dual-objective optimization.arXiv preprint arXiv:2503.03710, 2025.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models Improving llm safety alignment with dual-objective optimization.arXiv preprint arXiv:2503.03710, 2025

Reference 66

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3832bec-1717-443c-92c3-1f82758dfc20 · outbound

This paper cites AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models.

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models

Reference 67

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a82181ce-9afa-48ed-8741-11db055fdc6f · outbound

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

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models Instruction-Following Evaluation for Large Language Models

Reference 68

Resolution: unresolved; no resolver link, observed 2026-07-12T06:11:38.403281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers