Deliberative Alignment: Reasoning Enables Safer Language Models | Paper Citation Record

Observation 6ef9a4ad-f9b4-4eed-abe4-dde4c5d50bf1 · inbound

MoBA: Mixture of Block Attention for Long-Context LLMs cites this paper.

MoBA: Mixture of Block Attention for Long-Context LLMs Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 51

Resolution: metadata mismatch; arxiv_id, observed 2026-05-16T06:15:46.165967Z

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 797b4cde-8920-4277-8e1e-9c7bd552206a · inbound

LLM-Safety Evaluations Lack Robustness cites this paper.

LLM-Safety Evaluations Lack Robustness Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-05-23T01:27:21.396795Z

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 b5cb668e-a047-436e-8f98-c11c3d112395 · inbound

Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation cites this paper.

Monitoring Reasoning Models for Misbehavior and the Risks of Promoting Obfuscation Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 59

Resolution: verified exact; arxiv_id, observed 2026-05-21T07:24:12.967449Z

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 0764566c-4bae-4790-a32f-5248f95636f0 · inbound

Whispers of Many Shores: Cultural Alignment through Collaborative Cultural Expertise cites this paper.

Whispers of Many Shores: Cultural Alignment through Collaborative Cultural Expertise Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T12:13:21.052638Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d95336f-2acc-4672-83ab-f461671f1728 · inbound

Lossless Token Sequence Compression via Meta-Tokens cites this paper.

Lossless Token Sequence Compression via Meta-Tokens Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T12:14:26.266557Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0573b213-1033-4801-bd25-b42495bbc261 · inbound

Teaching an Old LLM Secure Coding: Localized Preference Optimization on Distilled Preferences cites this paper.

Teaching an Old LLM Secure Coding: Localized Preference Optimization on Distilled Preferences Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-07T12:10:30.276451Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 567b6b7a-433b-4046-8802-41b02ea292ce · inbound

A Red Teaming Roadmap Towards System-Level Safety cites this paper.

A Red Teaming Roadmap Towards System-Level Safety Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T12:11:19.235153Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d690aabc-7d87-4f24-929f-34c3c953e1ee · inbound

SafeCoT: Improving VLM Safety with Minimal Reasoning cites this paper.

SafeCoT: Improving VLM Safety with Minimal Reasoning Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T05:19:00.051825Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a952a564-86e3-4215-84b1-0e5002fc8b9b · inbound

InfoFlood: Jailbreaking Large Language Models with Information Overload cites this paper.

InfoFlood: Jailbreaking Large Language Models with Information Overload Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T01:02:28.553458Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2513c89-8d5f-42a1-a973-4811b3530d72 · inbound

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety cites this paper.

FORTRESS: Frontier Risk Evaluation for National Security and Public Safety Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T00:15:00.611082Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d78fe336-7b68-4781-a6de-0a99ff02065d · inbound

A Representation Engineering Perspective on the Effectiveness of Multi-Turn Jailbreaks cites this paper.

A Representation Engineering Perspective on the Effectiveness of Multi-Turn Jailbreaks Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-06T21:50:24.108617Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e922bb64-c738-4675-aed0-39776862d27a · inbound

SAND: Boosting LLM Agents with Self-Taught Action Deliberation cites this paper.

SAND: Boosting LLM Agents with Self-Taught Action Deliberation Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T18:47:19.985383Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 209be614-bf2f-4e4a-8152-18d0bb36ce4b · inbound

Think Clearly: Improving Reasoning via Redundant Token Pruning cites this paper.

Think Clearly: Improving Reasoning via Redundant Token Pruning Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T00:23:17.986195Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation efeff014-0da3-4387-89e2-6fc3a28658e7 · inbound

Subliminal Learning: Language models transmit behavioral traits via hidden signals in data cites this paper.

Subliminal Learning: Language models transmit behavioral traits via hidden signals in data Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T15:53:17.551777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

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

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning cites this paper.

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 415de428-35f3-4565-9940-7ce12511a372 · inbound

Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges cites this paper.

Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 283

Resolution: unresolved; no resolver link, observed 2026-08-06T14:13:07.297537Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b23d923-fb9a-45b2-9e6d-cf79ef6937c9 · inbound

Libra: Large Chinese-based Safeguard for AI Content cites this paper.

Libra: Large Chinese-based Safeguard for AI Content Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T12:17:38.663630Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5a3d952-e6d6-49f3-a72c-8cf9204b488b · inbound

R1-ACT: Efficient Reasoning Model Safety Alignment by Activating Safety Knowledge cites this paper.

R1-ACT: Efficient Reasoning Model Safety Alignment by Activating Safety Knowledge Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T10:18:24.466989Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 078762c1-6d06-4376-85a0-197877d02b1d · inbound

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning cites this paper.

Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 155

Resolution: unresolved; no resolver link, observed 2026-08-06T04:47:25.538461Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef1a2ba5-1e30-4db3-88ed-19856cf9274d · inbound

Towards terahertz nanomechanics cites this paper.

Towards terahertz nanomechanics Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T01:03:50.244026Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ef559a2-84e8-49b2-81d8-62ea5359e245 · inbound

ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants cites this paper.

ASTRA: Autonomous Spatial-Temporal Red-teaming for AI Software Assistants Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T01:04:33.591580Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1c86dd5-b54c-4c70-b9d3-856187e3ec0a · inbound

Whose Truth? Pluralistic Geo-Alignment for (Agentic) AI cites this paper.

Whose Truth? Pluralistic Geo-Alignment for (Agentic) AI Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-05T23:23:31.962576Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11e7454a-7858-43d9-98a1-03d479d9b806 · inbound

gpt-oss-120b & gpt-oss-20b Model Card cites this paper.

gpt-oss-120b & gpt-oss-20b Model Card Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 29

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T12:22:54.679028Z

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 80137bcd-470a-400a-b79a-4e705dcc8b32 · inbound

IntentionReasoner: Facilitating Adaptive LLM Safeguards through Intent Reasoning and Selective Query Refinement cites this paper.

IntentionReasoner: Facilitating Adaptive LLM Safeguards through Intent Reasoning and Selective Query Refinement Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-05T15:20:14.188064Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73b85185-a26e-4f6f-abc8-c828b1299b94 · inbound

Statutory Construction and Interpretation for Artificial Intelligence cites this paper.

Statutory Construction and Interpretation for Artificial Intelligence Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-05T12:52:54.701047Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 717369dd-b535-4414-a90e-5ed197e818ed · inbound

A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models cites this paper.

A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 152

Resolution: unresolved; no resolver link, observed 2026-08-05T10:39:07.027988Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f910b908-634e-4eb7-8108-e78f6441d5d2 · inbound

Between a Rock and a Hard Place: The Tension Between Ethical Reasoning and Safety Alignment in LLMs cites this paper.

Between a Rock and a Hard Place: The Tension Between Ethical Reasoning and Safety Alignment in LLMs Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-18T19:36:47.435169Z

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 812cb2d2-f762-48b8-92ff-288ab0b62199 · inbound

Between a Rock and a Hard Place: The Tension Between Ethical Reasoning and Safety Alignment in LLMs cites this paper.

Between a Rock and a Hard Place: The Tension Between Ethical Reasoning and Safety Alignment in LLMs Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-05T10:36:15.617560Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7661fd46-165e-4792-9ccc-10ba8412cae6 · inbound

SafeSearch: Automated Red-Teaming of LLM-Based Search Agents cites this paper.

SafeSearch: Automated Red-Teaming of LLM-Based Search Agents Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-04T14:43:49.835349Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce52139d-2018-4134-8251-1252b0e2ce92 · inbound

Reasoning Up the Instruction Ladder for Controllable Language Models cites this paper.

Reasoning Up the Instruction Ladder for Controllable Language Models Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-04T07:07:52.834565Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76760757-a24b-4d92-be01-fe907de2fc53 · inbound

Safety Alignment as Continual Learning: Mitigating the Alignment Tax via Orthogonal Gradient Projection cites this paper.

Safety Alignment as Continual Learning: Mitigating the Alignment Tax via Orthogonal Gradient Projection Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-16T06:40:42.343205Z

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 b26cf182-2e61-46b3-a1f3-1629fa03bffc · inbound

Contrastive Reasoning Alignment: Reinforcement Learning from Hidden Representations cites this paper.

Contrastive Reasoning Alignment: Reinforcement Learning from Hidden Representations Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 10

Resolution: metadata mismatch; arxiv_id, observed 2026-05-21T11:24:08.445919Z

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 ed444e7a-71c3-4c47-a1fc-47ab4227d11f · inbound

Human Values Matter: Investigating How Misalignment Shapes Collective Behaviors in LLM Agent Communities cites this paper.

Human Values Matter: Investigating How Misalignment Shapes Collective Behaviors in LLM Agent Communities Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 4

Resolution: metadata mismatch; arxiv_id, observed 2026-05-10T22:25:51.877085Z

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 414ce9e4-f3f5-49b9-a2fe-8e74c4f7c7a2 · inbound

Think Before You Code: Dual Reasoning for the NLSafety-Utility Trade-Off in LLM Code Generation cites this paper.

Think Before You Code: Dual Reasoning for the NLSafety-Utility Trade-Off in LLM Code Generation Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-11T09:56:03.213083Z

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 26d3d840-1830-414c-9e64-2f30f50431db · inbound

Think Before You Code: Dual Reasoning for the NLSafety-Utility Trade-Off in LLM Code Generation cites this paper.

Think Before You Code: Dual Reasoning for the NLSafety-Utility Trade-Off in LLM Code Generation Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-03T00:19:56.880861Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f5fbc12d-ebfa-4525-a4d1-a21615b3988b · inbound

IYKYK (But AI Doesn't): Automated Content Moderation Does Not Capture Communities' Heterogeneous Attitudes Towards Reclaimed Language cites this paper.

IYKYK (But AI Doesn't): Automated Content Moderation Does Not Capture Communities' Heterogeneous Attitudes Towards Reclaimed Language Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 39

Resolution: verified exact; arxiv_id, observed 2026-05-10T08:22:37.099023Z

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 17fe05f8-fa6c-4f9a-957e-3e1ef5b721d5 · inbound

Terminal Wrench: A Dataset of 331 Reward-Hackable Environments and 3,632 Exploit Trajectories cites this paper.

Terminal Wrench: A Dataset of 331 Reward-Hackable Environments and 3,632 Exploit Trajectories Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-10T05:51:10.098655Z

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 27bc220b-5f2e-4b0e-8fcc-df1df3f8a7af · inbound

Reasoning Structure Matters for Safety Alignment of Reasoning Models cites this paper.

Reasoning Structure Matters for Safety Alignment of Reasoning Models Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 25

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T12:56:04.339490Z

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 c8701d36-fcba-4409-85cc-d5bb4047210b · inbound

Contextual Multi-Objective Optimization: Rethinking Objectives in Frontier AI Systems cites this paper.

Contextual Multi-Objective Optimization: Rethinking Objectives in Frontier AI Systems Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 19

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T23:41:18.981416Z

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 e64a7095-35c2-462c-b0ae-e9560148d988 · inbound

One Turn Too Late: Response-Aware Defense Against Hidden Malicious Intent in Multi-Turn Dialogue cites this paper.

One Turn Too Late: Response-Aware Defense Against Hidden Malicious Intent in Multi-Turn Dialogue Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 8

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T19:41:09.007290Z

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 e132bfc6-f458-4968-bb02-2054c8aeab10 · inbound

One Turn Too Late: Response-Aware Defense Against Hidden Malicious Intent in Multi-Turn Dialogue cites this paper.

One Turn Too Late: Response-Aware Defense Against Hidden Malicious Intent in Multi-Turn Dialogue Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 8

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T07:57:31.670860Z

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 35d8e2ed-d827-4192-9da9-8eaedc0b0e00 · inbound

Chain of Risk: Safety Failures in Large Reasoning Models and Mitigation via Adaptive Multi-Principle Steering cites this paper.

Chain of Risk: Safety Failures in Large Reasoning Models and Mitigation via Adaptive Multi-Principle Steering Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 6

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T19:31:08.576351Z

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 479779e5-6147-404b-84aa-3e672a7f678a · inbound

Internalizing Safety Understanding in Large Reasoning Models via Verification cites this paper.

Internalizing Safety Understanding in Large Reasoning Models via Verification Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-12T01:51:14.318720Z

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 272fc79d-4ef2-4ae5-ba07-222ec5920666 · inbound

Understanding Goal Generalisation in Sequential Reinforcement Learning cites this paper.

Understanding Goal Generalisation in Sequential Reinforcement Learning Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-25T04:50:20.921471Z

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 7f4d29f4-5a4d-4ba7-a7c7-0bbc2ddd70f1 · inbound

How Well Do Models Follow Their Constitutions? cites this paper.

How Well Do Models Follow Their Constitutions? Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-06-30T15:34:47.874528Z

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 cdfbb531-120e-466a-b884-6941277f5414 · inbound

Reflect-Guard: Enhancing LLM Safeguards against Adversarial Prompts via Logical Self-Reflection cites this paper.

Reflect-Guard: Enhancing LLM Safeguards against Adversarial Prompts via Logical Self-Reflection Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 2

Resolution: verified exact; arxiv_id, observed 2026-07-01T16:35:50.610720Z

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 ba830e08-2ec1-429e-ba58-0d5e4ad252e6 · inbound

Mitigating Adaptive Attacks against Reasoning Models with Activation Consistency Training cites this paper.

Mitigating Adaptive Attacks against Reasoning Models with Activation Consistency Training Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-06-29T14:23:30.706723Z

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 261b5b94-bf0f-4a3a-b4cb-96c188b31576 · inbound

Characterize Then Distill: Mechanistic Reasoning in Large Output Spaces cites this paper.

Characterize Then Distill: Mechanistic Reasoning in Large Output Spaces Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 100

Resolution: verified exact; arxiv_id, observed 2026-06-27T22:31:21.526096Z

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 9967d366-91e4-4062-8624-8761f1e45cc6 · inbound

Activation Steering Induces Emergent Misalignment: A More Comprehensive Evaluation cites this paper.

Activation Steering Induces Emergent Misalignment: A More Comprehensive Evaluation Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-07-02T22:57:26.124147Z

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 0a3bd05e-3e5b-42b0-866e-0586952688a2 · inbound

Proxy Reward Internalization and Mechanistic Exploitation: A Learned Precursor to Reward Hacking and Its Generalization cites this paper.

Proxy Reward Internalization and Mechanistic Exploitation: A Learned Precursor to Reward Hacking and Its Generalization Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 244

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T01:37:30.453603Z

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 bd46bb0c-007c-4699-a9ec-b322b81061fc · inbound

Greedy Coordinate Diffusion: Effective and Semantically Coherent Adversarial Attacks via Diffusion Guidance cites this paper.

Greedy Coordinate Diffusion: Effective and Semantically Coherent Adversarial Attacks via Diffusion Guidance Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 17

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T17:08:43.430699Z

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 adb4d015-68ac-43f9-bbdb-4708714ccbe5 · inbound

Analyzing Defensive Misdirection Against Model-Guided Automated Attacks on Agentic AI Systems cites this paper.

Analyzing Defensive Misdirection Against Model-Guided Automated Attacks on Agentic AI Systems Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 11

Resolution: metadata mismatch; arxiv_id, observed 2026-07-04T04:19:34.767260Z

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 043c0c62-8bf8-42ae-b1ee-ea97acc3187d · inbound

Analyzing Defensive Misdirection Against Model-Guided Automated Attacks on Agentic AI Systems cites this paper.

Analyzing Defensive Misdirection Against Model-Guided Automated Attacks on Agentic AI Systems Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-06-30T10:34:36.560267Z

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 125b2c5f-13ce-4795-8bb9-9e81e6ad67a1 · inbound

Do Thinking Tokens Help with Safety? cites this paper.

Do Thinking Tokens Help with Safety? Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 7

Resolution: metadata mismatch; arxiv_id, observed 2026-07-04T17:30:00.639214Z

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 8e26d784-e1d1-4784-a47d-feedb03f575d · inbound

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

PolicyAlign: Direct Policy-Based Safety Alignment for Large Language Models Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 17

Resolution: metadata mismatch; arxiv_id, observed 2026-07-04T19:40:06.722457Z

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 872dc00c-6b2b-4f47-8a70-0014c8a804a7 · inbound

Agent Safety Is Action Alignment cites this paper.

Agent Safety Is Action Alignment Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-06-30T09:54:35.001200Z

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 1d0be5d4-c9cd-4fef-8161-6bc4d6f3d461 · inbound

HARC: Coupling Harmfulness and Refusal Directions for Robust Safety Alignment cites this paper.

HARC: Coupling Harmfulness and Refusal Directions for Robust Safety Alignment Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 15

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T13:06:58.846398Z

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 9b2a054d-3b7f-4ee8-bccf-a3d47cd92f47 · inbound

HARC: Coupling Harmfulness and Refusal Directions for Robust Safety Alignment cites this paper.

HARC: Coupling Harmfulness and Refusal Directions for Robust Safety Alignment Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-12T09:27:01.450708Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c34d92c6-d355-4da5-a9f0-5f14463cc273 · inbound

Cognitive Firewall: A Proactive, Zero-Trust, Multi-Gate Framework for LLM Safety cites this paper.

Cognitive Firewall: A Proactive, Zero-Trust, Multi-Gate Framework for LLM Safety Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 15

Resolution: metadata mismatch; arxiv_id, observed 2026-07-03T20:38:54.934420Z

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 b9561dc8-97ce-42f3-af4f-499781103678 · inbound

Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models cites this paper.

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 5be75692-127e-4334-b317-c72f709d75c2 · inbound

Position: Preventing AI-Generated CSAM Necessitates New Approaches to AI Safety cites this paper.

Position: Preventing AI-Generated CSAM Necessitates New Approaches to AI Safety Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 99

Resolution: unresolved; no resolver link, observed 2026-07-12T14:28:50.627444Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c8e5ee8-1db0-4ee8-b32e-b1651172bed9 · inbound

Cost of Reasoning in non-English Languages: A Case Study on Japanese cites this paper.

Cost of Reasoning in non-English Languages: A Case Study on Japanese Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-14T14:12:44.286699Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6aed98b-cb00-497b-991a-2288d69fe821 · inbound

Underwriting the Agent Economy: The Blueprint for an AI Insurance Stack cites this paper.

Underwriting the Agent Economy: The Blueprint for an AI Insurance Stack Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 230

Resolution: unresolved; no resolver link, observed 2026-07-15T08:35:47.870083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a01fcd39-8be5-4f88-84ba-1f363099a19e · inbound

Underwriting the Agent Economy: The Blueprint for an AI Insurance Stack cites this paper.

Underwriting the Agent Economy: The Blueprint for an AI Insurance Stack Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 231

Resolution: unresolved; no resolver link, observed 2026-08-02T06:46:40.391719Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d406d612-cdeb-4712-a465-bb94445022c3 · inbound

Verbalizable Representations Form a Global Workspace in Language Models cites this paper.

Verbalizable Representations Form a Global Workspace in Language Models Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-01T23:15:23.274320Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4492457e-d1d8-4fe6-ac1c-0f87fa2c6a30 · inbound

A Geometric Perspective on Stabilizing Value Conflict Resolution cites this paper.

A Geometric Perspective on Stabilizing Value Conflict Resolution Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-01T16:35:30.952522Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79cea9df-6c32-4571-bcc4-7adcd1b3fb91 · inbound

QuantiBias: Benchmarking Quantization-Induced Bias in LLMs cites this paper.

QuantiBias: Benchmarking Quantization-Induced Bias in LLMs Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-01T08:38:55.560417Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4c5bf99-e663-4e71-8425-5902ed995ed8 · inbound

Shared SFT Lessons Across Alignment, Model Organisms, and Toy Models cites this paper.

Shared SFT Lessons Across Alignment, Model Organisms, and Toy Models Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-01T00:38:41.667721Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78a191ed-6886-4149-8e7f-11aeed5beb12 · inbound

Constitutional Midtraining: Content Presence Drives Alignment Gains cites this paper.

Constitutional Midtraining: Content Presence Drives Alignment Gains Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-01T11:35:00.225163Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db5790cb-4fa6-40dc-a93d-2b4355464f2f · inbound

Chain-of-Models: Cross-Model Auditing for Bias-Robust LLM Judges cites this paper.

Chain-of-Models: Cross-Model Auditing for Bias-Robust LLM Judges Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-03T00:55:26.100966Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77fe7ada-8310-426f-8ddf-ff0fc104378d · inbound

Outcome-Guided Distillation: A Teacher-Student Framework to Advance VLM Reasoning in Autonomous Driving cites this paper.

Outcome-Guided Distillation: A Teacher-Student Framework to Advance VLM Reasoning in Autonomous Driving Deliberative Alignment: Reasoning Enables Safer Language Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-03T14:38:56.180832Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers