mlsanityData to 7 Oct 2026

STAR-S: Improving Safety Alignment through Self-Taught Reasoning on Safety Rules

arXiv 2601.03537 ↗First posted 7 Jan 2026cs.AI cs.CLcited by 2

On the map: LLM reasoning → Reasoning for agents, planning and code

also in 2 more
Abstract (arXiv)

Defending against jailbreak attacks is crucial for the safe deployment of Large Language Models (LLMs). Recent research has attempted to improve safety by training models to reason over safety rules before responding. However, a key issue lies in determining what form of safety reasoning effectively defends against jailbreak attacks, which is difficult to explicitly design or directly obtain. To address this, we propose STAR-S (Self-TAught Reasoning based on Safety rules), a framework that integrates the learning of safety rule reasoning into a self-taught loop. The core of STAR-S involves eliciting reasoning and reflection guided by safety rules, then leveraging fine-tuning to enhance safety reasoning. Repeating this process creates a synergistic cycle. Improvements in the model's reasoning and interpretation of safety rules allow it to produce better reasoning data under safety rule prompts, which is then utilized for further training. Experiments show that STAR-S effectively defends against jailbreak attacks, outperforming baselines. Code is available at: https://github.com/pikepokenew/STARS.git.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. Builds on 34 of its 39 references that are in the map. First posted on arXiv 7 Jan 2026.

Builds on

34 of 39 references.

Closest ancestors · 9

Same direction, newest first

  1. 2025Large Reasoning Models Learn Better Alignment from Flawed Thinking1 Oct
  2. 2025SPC: Evolving Self-Play Critic via Adversarial Games for LLM Reasoning27 Apr
  3. 2025RealSafe-R1: Safety-Aligned DeepSeek-R1 without Compromising Reasoning Capability14 Apr
  4. 2025STAR-1: Safer Alignment of Reasoning LLMs with 1K Data2 Apr
  5. 2025Safety is Not Only About Refusal: Reasoning-Enhanced Fine-tuning for Interpretable LLM Safety6 Mar
  6. 2025Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable1 Mar
  7. 2025STAIR: Improving Safety Alignment with Introspective Reasoning4 Feb
  8. 2025Trading Inference-Time Compute for Adversarial Robustness31 Jan
  9. 2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code12 Mar

Other references · 25

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  3. 2018Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challengecited by 4,710
  4. 2023Let's Verify Step by Stepcited by 3,598
  5. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 2,914
  6. 2023Jailbroken: How Does LLM Safety Training Fail?cited by 1,565
  7. 2024LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Modelscited by 1,442
  8. 2023Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!cited by 1,106
  9. 2024ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Toolscited by 1,096
  10. 2022Large Language Models Can Self-Improvecited by 656
  11. 2023Tree of Attacks: Jailbreaking Black-Box LLMs Automaticallycited by 619
  12. 2024Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Modelscited by 552
13 more
  1. 2023Reinforced Self-Training (ReST) for Language Modelingcited by 486
  2. 2025GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Modelscited by 446
  3. 2025Cognitive Behaviors that Enable Self-Improving Reasoners, or, Four Habits of Highly Effective STaRscited by 373
  4. 2023DeepInception: Hypnotize Large Language Model to Be Jailbreakercited by 337
  5. 2023A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easilycited by 242
  6. 2024SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decodingcited by 233
  7. 2024SALAD-Bench: A Hierarchical and Comprehensive Safety Benchmark for Large Language Modelscited by 225
  8. 2024GradSafe: Detecting Jailbreak Prompts for LLMs via Safety-Critical Gradient Analysiscited by 87
  9. 2024InferAligner: Inference-Time Alignment for Harmlessness through Cross-Model Guidancecited by 78
  10. 2024CodeAttack: Revealing Safety Generalization Challenges of Large Language Models via Code Completioncited by 70
  11. 2024Physics of Language Models: Part 2.2, How to Learn From Mistakes on Grade-School Math Problemscited by 49
  12. 2025Trade-offs in Large Reasoning Models: An Empirical Analysis of Deliberative and Adaptive Reasoning over Foundational Capabilitiescited by 20
  13. 2024Course-Correction: Safety Alignment Using Synthetic Preferencescited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Mitigating the Safety-utility Trade-off in LLM Alignment via Adaptive Safe Context Learningcited by 2
  2. 2026Deferred Exposure of Future Trajectories for Verifiable Reasoning in Autonomous Driving VLMscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Reasoning-to-Defend: Safety-Aware Reasoning Can Defend Large Language Models from Jailbreaking
  2. 2025Reasoned Safety Alignment: Ensuring Jailbreak Defense via Answer-Then-Check
  3. 2025Self-Jailbreaking: Language Models Can Reason Themselves Out of Safety Alignment After Benign Reasoning Training
  4. 2025When Models Outthink Their Safety: Unveiling and Mitigating Self-Jailbreak in Large Reasoning Models
  5. 2025Enhancing Model Defense Against Jailbreaks with Proactive Safety Reasoning
  6. 2025SafeBehavior: Simulating Human-Like Multistage Reasoning to Mitigate Jailbreak Attacks in Large Language Models
  7. 2025ARMOR: Aligning Secure and Safe Large Language Models via Meticulous Reasoning
  8. 2025RAJ-PGA: Reasoning-Activated Jailbreak and Principle-Guided Alignment Framework for Large Reasoning Models