Cover Image

Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kumarage, Tharindu, Mehrabi, Ninareh, Ramakrishna, Anil, Zhao, Xinyan, Zemel, Richard, Chang, Kai-Wei, Galstyan, Aram, Gupta, Rahul, Peris, Charith
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Kaleidoscopic Teaming in Multi Agent Simulations
by: Mehrabi, Ninareh, et al.
Published: (2025)

K-Edit: Language Model Editing with Contextual Knowledge Awareness
by: Markowitz, Elan, et al.
Published: (2025)

Attribute Controlled Fine-tuning for Large Language Models: A Case Study on Detoxification
by: Meng, Tao, et al.
Published: (2024)

Tree-of-Traversals: A Zero-Shot Reasoning Algorithm for Augmenting Black-box Language Models with Knowledge Graphs
by: Markowitz, Elan, et al.
Published: (2024)

On the steerability of large language models toward data-driven personas
by: Li, Junyi, et al.
Published: (2023)

ARES: Adaptive Red-Teaming and End-to-End Repair of Policy-Reward System
by: Liang, Jiacheng, et al.
Published: (2026)

SWAN: Semantic Watermarking with Abstract Meaning Representation
by: Ye, Ziping, et al.
Published: (2026)

Data Advisor: Dynamic Data Curation for Safety Alignment of Large Language Models
by: Wang, Fei, et al.
Published: (2024)

Emergent Strategic Reasoning Risks in AI: A Taxonomy-Driven Evaluation Framework
by: Kumarage, Tharindu, et al.
Published: (2026)

Tokenization Matters: Navigating Data-Scarce Tokenization for Gender Inclusive Language Technologies
by: Ovalle, Anaelia, et al.
Published: (2023)

FLIRT: Feedback Loop In-context Red Teaming
by: Mehrabi, Ninareh, et al.
Published: (2023)

Partial Federated Learning
by: Feng, Tiantian, et al.
Published: (2024)

Prompt Perturbation Consistency Learning for Robust Language Models
by: Qiang, Yao, et al.
Published: (2024)

DiCoRe: Enhancing Zero-shot Event Detection via Divergent-Convergent LLM Reasoning
by: Parekh, Tanmay, et al.
Published: (2025)

Evaluating the Critical Risks of Amazon's Nova Premier under the Frontier Model Safety Framework
by: Krishna, Satyapriya, et al.
Published: (2025)

Can Knowledge Graphs Reduce Hallucinations in LLMs? : A Survey
by: Agrawal, Garima, et al.
Published: (2023)

Diagnosing Memorization in Chain-of-Thought Reasoning, One Token at a Time
by: Li, Huihan, et al.
Published: (2025)

Harnessing Artificial Intelligence to Combat Online Hate: Exploring the Challenges and Opportunities of Large Language Models in Hate Speech Detection
by: Kumarage, Tharindu, et al.
Published: (2024)

Strategize Globally, Adapt Locally: A Multi-Turn Red Teaming Agent with Dual-Level Learning
by: Chen, Si, et al.
Published: (2025)

Robust Persona-Aware Toxicity Detection with Prompt Optimization and Learned Ensembling
by: Atil, Berk, et al.
Published: (2026)

Mindful-RAG: A Study of Points of Failure in Retrieval Augmented Generation
by: Agrawal, Garima, et al.
Published: (2024)

CoT Vectors: Transferring and Probing the Reasoning Mechanisms of LLMs
by: Li, Li, et al.
Published: (2025)

Not Every Token Needs Forgetting: Selective Unlearning to Limit Change in Utility in Large Language Model Unlearning
by: Wan, Yixin, et al.
Published: (2025)

Asymmetric Phase Coding Audio Watermarking
by: Yang, Guang, et al.
Published: (2026)

FERRET: Framework for Expansion Reliant Red Teaming
by: Mehrabi, Ninareh, et al.
Published: (2026)

MINT-CoT: Enabling Interleaved Visual Tokens in Mathematical Chain-of-Thought Reasoning
by: Chen, Xinyan, et al.
Published: (2025)

How Likely Do LLMs with CoT Mimic Human Reasoning?
by: Bao, Guangsheng, et al.
Published: (2024)

Reasoning as an Attack Surface: Adaptive Evolutionary CoT Jailbreaks for LLMs
by: Li, Jianan, et al.
Published: (2026)

From Narrow Unlearning to Emergent Misalignment: Causes, Consequences, and Containment in LLMs
by: Mushtaq, Erum, et al.
Published: (2025)

KG-LLM-Bench: A Scalable Benchmark for Evaluating LLM Reasoning on Textualized Knowledge Graphs
by: Markowitz, Elan, et al.
Published: (2025)

S3-CoT: Self-Sampled Succinct Reasoning Enables Efficient Chain-of-Thought LLMs
by: Du, Yanrui, et al.
Published: (2026)

Cross-Platform Hate Speech Detection with Weakly Supervised Causal Disentanglement
by: Sheth, Paras, et al.
Published: (2024)

Assessing Visual Privacy Risks in Multimodal AI: A Novel Taxonomy-Grounded Evaluation of Vision-Language Models
by: Tsaprazlis, Efthymios, et al.
Published: (2025)

Co-Evolving Agents: Learning from Failures as Hard Negatives
by: Jung, Yeonsung, et al.
Published: (2025)

Unsupervised Confidence Calibration for Reasoning LLMs from a Single Generation
by: Zollo, Thomas, et al.
Published: (2026)

LLMs for Game Theory: Entropy-Guided In-Context Learning and Adaptive CoT Reasoning
by: Banfi, Tommaso Felice, et al.
Published: (2026)

Making Sense Of Distributed Representations With Activation Spectroscopy
by: Reing, Kyle, et al.
Published: (2025)

Learning Morphisms with Gauss-Newton Approximation for Growing Networks
by: Lawton, Neal, et al.
Published: (2024)

Privacy-preserved LLM Cascade via CoT-enhanced Policy Learning
by: Zhang, Kai, et al.
Published: (2024)

Can LLMs Improve Multimodal Fact-Checking by Asking Relevant Questions?
by: Beigi, Alimohammad, et al.
Published: (2024)