mlsanityData to 7 Oct 2026

Efficient Safety Alignment of Language Models via Latent Personality Traits

arXiv 2607.07918 ↗First posted 8 Jul 2026cs.LG cs.AI cs.CLcited by 0

On the map: LLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks

also in 1 more
Abstract (arXiv)

Current safety methods for large language models are known to be vulnerable to adversarial attacks, motivating research into robust alternatives. Latent Adversarial Training (LAT) is among the most effective defenses, but can degrade utility and requires training on large datasets of harmful prompts. We introduce Latent Personality Alignment (LPA), which replaces explicit harm refusal with adversarial training on just 66 harm-agnostic statements drawn from psychometric personality literature. We hypothesize that personality-anchored representations share latent structure with harm avoidance, so adversarially stabilizing them implicitly constrains the subspace exploited by jailbreak attacks. LPA achieves near-zero attack success rates on HarmBench across direct requests and five jailbreak methods, despite never seeing harmful content during training and no loss of performance on standard benchmarks. Moreover, the training process is lightweight; the entire procedure completes in minutes on a single GPU and uses 75x fewer examples than standard LAT. Extensive ablations demonstrate the robustness, efficiency, and generalization of our method.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Safety alignment and jailbreak attacks, one of 10 directions in LLM alignment / RLHF / preference optimisation. Builds on 37 of its 55 references that are in the map. First posted on arXiv 8 Jul 2026.

Builds on

37 of 55 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025Latent-space adversarial training with post-aware calibration for defending large language models against jailbreak attacks18 Jan
  2. 2024OR-Bench: An Over-Refusal Benchmark for Large Language Models31 May
  3. 2023Universal and Transferable Adversarial Attacks on Aligned Language Models27 Jul

Other references · 34

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  3. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  4. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  5. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  6. 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,919
  7. 2024HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusalcited by 1,330
  8. 2023Jailbreaking Black Box Large Language Models in Twenty Queriescited by 1,326
  9. 2016The LAMBADA dataset: Word prediction requiring a broad discourse contextcited by 960
  10. 2023Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formattingcited by 778
  11. 2017Crowdsourcing Multiple Choice Science Questionscited by 742
  12. 2023Tree of Attacks: Jailbreaking Black-Box LLMs Automaticallycited by 619
22 more
  1. 2025Persona Vectors: Monitoring and Controlling Character Traits in Language Modelscited by 303
  2. 2024tinyBenchmarks: evaluating LLMs with fewer examplescited by 295
  3. 2024Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Promptscited by 189
  4. 2024Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMscited by 158
  5. 2025Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMscited by 158
  6. 2024AdvPrompter: Fast Adaptive Adversarial Prompting for LLMscited by 146
  7. 2022Evaluating and Inducing Personality in Pre-trained Language Modelscited by 122
  8. 2024Efficient Adversarial Training in LLMs with Continuous Attackscited by 104
  9. 2024The Butterfly Effect of Altering Prompts: How Small Changes and Jailbreaks Affect Large Language Model Performancecited by 97
  10. 2024Defending Against Unforeseen Failure Modes with Latent Adversarial Trainingcited by 82
  11. 2024What Makes and Breaks Safety Fine-tuning? A Mechanistic Studycited by 54
  12. 2023Self-Assessment Tests are Unreliable Measures of LLM Personalitycited by 39
  13. 2024Personality Alignment of Large Language Modelscited by 36
  14. 2024SysBench: Can Large Language Models Follow System Messages?cited by 26
  15. 2025Persistent Instability in LLM's Personality Measurements: Effects of Scale, Reasoning, and Conversation Historycited by 25
  16. 2026A Coin Flip for Safety: LLM Judges Fail to Reliably Measure Adversarial Robustnesscited by 20
  17. 2024An Interpretable N-gram Perplexity Threat Model for Large Language Model Jailbreakscited by 10
  18. 2025Bullying the Machine: How Personas Increase LLM Vulnerabilitycited by 8
  19. 2026Stable and Explainable Personality Trait Evaluation in Large Language Models with Internal Activationscited by 8
  20. 2026Evaluating Alignment of Behavioral Dispositions in LLMscited by 6
  21. 2025Evaluating LLM Alignment on Personality Inference from Real-World Interview Datacited by 4
  22. 2025Psychometric Personality Shaping Modulates Capabilities and Safety in Language Modelscited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Latent Personality Alignment: Improving Harmlessness Without Mentioning Harms
  2. 2025Probing the Robustness of Large Language Models Safety to Latent Perturbations
  3. 2026Safety Is Not Universal: The Selective Safety Trap in LLM Alignment
  4. 2026Target-free Latent Safety Alignment
  5. 2026Understanding the Effects of Safety Unalignment on Large Language Models
  6. 2025In-Training Defenses against Emergent Misalignment in Language Models
  7. 2025LatentGuard: Controllable Latent Steering for Robust Refusal of Attacks and Reliable Response Generation
  8. 2025Scaling Patterns in Adversarial Alignment: Evidence from Multi-LLM Jailbreak Experiments