mlsanityData to 14 Oct 2026

N-GLARE: An Non-Generative Latent Representation-Efficient LLM Safety Evaluator

arXiv 2511.14195 ↗First posted 18 Nov 2025cs.LG cs.CRcited by 1

On the map: LLM safety and security → Safety alignment, refusal and guardrails

Abstract (arXiv)

Evaluating the safety robustness of LLMs is critical for their deployment. However, mainstream Red Teaming methods rely on online generation and black-box output analysis. These approaches are not only costly but also suffer from feedback latency, making them unsuitable for agile diagnostics after training a new model. To address this, we propose N-GLARE (A Non-Generative, Latent Representation-Efficient LLM Safety Evaluator). N-GLARE operates entirely on the model's latent representations, bypassing the need for full text generation. It characterizes hidden layer dynamics by analyzing the APT (Angular-Probabilistic Trajectory) of latent representations and introducing the JSS (Jensen-Shannon Separability) metric. Experiments on over 40 models and 20 red teaming strategies demonstrate that the JSS metric exhibits high consistency with the safety rankings derived from Red Teaming. N-GLARE reproduces the discriminative trends of large-scale red-teaming tests at less than 1% of the token cost and the runtime cost, providing an efficient output-free evaluation proxy for real-time diagnostics.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Safety alignment, refusal and guardrails, one of 12 directions in LLM safety and security. Builds on 35 of its 45 references that are in the map. First posted on arXiv 18 Nov 2025.

Builds on

35 of 45 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Refusal in Language Models Is Mediated by a Single Direction17 Jun

Other references · 34

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  3. 2019BioBERT: a pre-trained biomedical language representation model for biomedical text miningcited by 1,947
  4. 2023Jailbroken: How Does LLM Safety Training Fail?cited by 1,651
  5. 2023Representation Engineering: A Top-Down Approach to AI Transparencycited by 1,336
  6. 2023Inference-Time Intervention: Eliciting Truthful Answers from a Language Modelcited by 1,302
  7. 2021Perceiver: General Perception with Iterative Attentioncited by 1,104
  8. 2023Steering Llama 2 via Contrastive Activation Additioncited by 1,085
  9. 2019BERT Rediscovers the Classical NLP Pipelinecited by 1,059
  10. 2019Are Sixteen Heads Really Better than One?cited by 816
  11. 2020A Primer in BERTology: What we know about how BERT workscited by 815
  12. 2023The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasetscited by 712
22 more
  1. 2023GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Promptscited by 560
  2. 2024Great, Now Write an Article About That: The Crescendo Multi-Turn LLM Jailbreak Attackcited by 390
  3. 2019A Multiscale Visualization of Attention in the Transformer Modelcited by 292
  4. 2024Security and Privacy Challenges of Large Language Models: A Surveycited by 186
  5. 2024AdvPrompter: Fast Adaptive Adversarial Prompting for LLMscited by 156
  6. 2024Attacks, Defenses and Evaluations for LLM Conversation Safety: A Surveycited by 130
  7. 2025X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-Agentscited by 125
  8. 2024AutoAttacker: A Large Language Model Guided System to Implement Automatic Cyber-attackscited by 96
  9. 2024Fast Adversarial Attacks on Language Models In One GPU Minutecited by 88
  10. 2024LLMs know their vulnerabilities: Uncover Safety Gaps through Natural Distribution Shiftscited by 86
  11. 2024InferAligner: Inference-Time Alignment for Harmlessness through Cross-Model Guidancecited by 83
  12. 2024Large Language Model (LLM) for Telecommunications: A Comprehensive Survey on Principles, Key Techniques, and Opportunitiescited by 83
  13. 2024Adaptive Activation Steering: A Tuning-Free LLM Truthfulness Improvement Method for Diverse Hallucinations Categoriescited by 77
  14. 2024Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systemscited by 66
  15. 2024Against The Achilles' Heel: A Survey on Red Teaming for Generative Modelscited by 59
  16. 2025Foot-In-The-Door: A Multi-turn Jailbreak for LLMscited by 54
  17. 2024Revisiting Jailbreaking for Large Language Models: A Representation Engineering Perspectivecited by 48
  18. 2024Model Surgery: Modulating LLM's Behavior Via Simple Parameter Editingcited by 23
  19. 2024Do LLMs Know to Respect Copyright Notice?cited by 13
  20. 2025CoRE: Enhancing Metacognition with Label-free Self-evaluation in LRMscited by 5
  21. 2024Self-Control of LLM Behaviors by Compressing Suffix Gradient into Prefix Controllercited by 3
  22. 2025Human-AI Collaboration or Academic Misconduct? Measuring AI Use in Student Writing Through Stylometric Evidencecited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Before the Last Token: Diagnosing Final-Token Safety Probe Failurescited by 3

Similar, not cited

Close in wording, no citation either way

  1. 2025SIRAJ: Diverse and Efficient Red-Teaming for LLM Agents via Distilled Structured Reasoning
  2. 2025RADAR: A Risk-Aware Dynamic Multi-Agent Framework for LLM Safety Evaluation via Role-Specialized Collaboration
  3. 2026REDAgentBench: Executable Red Teaming and Faithful Measurement of LLM Agent Systems
  4. 2025LLM-Safety Evaluations Lack Robustness
  5. 2026EvalSafetyGap: A Hybrid Survey and Conceptual Framework for LLM Evaluation-Safety Failures
  6. 2025AutoODD: Agentic Audits via Bayesian Red Teaming in Black-Box Models
  7. 2026OpenRT: An Open-Source Red Teaming Framework for Multimodal LLMs
  8. 2025A Red Teaming Roadmap Towards System-Level Safety