Efficient Safety Alignment of Language Models via Latent Personality Traits

[2607.07918] Efficient Safety Alignment of Language Models via Latent Personality Traits Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Machine Learning arXiv:2607.07918 (cs) [Submitted on 8 Jul 2026 ( v1 ), last revised 14 Aug 2026 (this version, v2)] Title: Efficient Safety Alignment of Language Models via Latent Personality Traits Authors: Mohamed Amine Merzouk , Nolan Smyth , Damiano Fornasiere , Linh Le , David Williams-King , Adam Oberman View a PDF of the paper titled Efficient Safety Alignment of Language Models via Latent Personality Traits, by Mohamed Amine Merzouk and 5 other authors View PDF HTML (experimental) Abstract: 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. Comments: 19 pages, 6 figures. Published as a conference paper at COLM 2026 Subjects: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Cryptography and Security (cs.CR) Cite as: arXiv:2607.07918 [cs.LG] (or arXiv:2607.07918v2 [cs.LG] for this version) https://doi.org/10.48550/arXiv.2607.07918 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Adam Oberman [ view email ] [v1] Wed, 8 Jul 2026 21:03:27 UTC (153 KB) [v2] Fri, 14 Aug 2026 18:25:59 UTC (156 KB) Full-text links: Access Paper: View a PDF of the paper titled Efficient Safety Alignment of Language Models via Latent Personality Traits, by Mohamed Amine Merzouk and 5 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.LG < prev | next > new | recent | 2026-07 Change to browse by: cs cs.AI cs.CL cs.CR References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) IArxiv recommender toggle IArxiv Recommender ( What is IArxiv? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Efficient Safety Alignment of Language Models via Latent Personality Traits#608927
• Efficient Safety Alignment of Language Models via Latent Personality Traits#352999
• SafeTutors: Benchmarking Pedagogical Safety in AI Tutoring Systems#1064893
• AgentBoundary: Counterfactual Evaluation of Safety in Tool-Using LLM Agents#1118731
• BabelSteering: Multilingual Safety Alignment via English Steering Vectors#625155