HarmProfile: Characterizing Harmful Distributions in Frontier LLMs

[2608.14577] HarmProfile: Characterizing Harmful Distributions in Frontier LLMs Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Computation and Language arXiv:2608.14577 (cs) [Submitted on 11 Jun 2026] Title: HarmProfile: Characterizing Harmful Distributions in Frontier LLMs Authors: Zhouyuan Ma , Yutao Wu , Hanxun Huang , Xiang Zheng , Xiao Liu , Yixin Cao , Zuxuan Wu , Xingjun Ma , Yu-Gang Jiang View a PDF of the paper titled HarmProfile: Characterizing Harmful Distributions in Frontier LLMs, by Zhouyuan Ma and 8 other authors View PDF HTML (experimental) Abstract: Frontier large language models (LLMs) safety evaluation has largely treated harmful generation as an attack outcome rather than as an object of analysis. Consequently, little is known about the harmful outputs produced during model misbehavior, partly because large-scale, high-quality collections of frontier-LLM misbehavior are difficult to obtain. To address this gap, we introduce HarmProfile, a content-centric benchmark dataset that collects model misbehavior across diverse harm categories and model families, and defines the resulting harmful-output distribution as a model-level risk profile. The premise is that, just as linguistic behavior can be characterized from an utterance corpus, model risk can be characterized from the content, severity, and variation of its safety failures. HarmProfile contains over 80,000 validated artifacts from 23 frontier LLMs across 13 model families, organized into 15 harm categories and 57 subcategories. Using this corpus, we find that frontier LLMs reliably produce harmful content at scale, yet exhibit distinct risk profiles; both harmfulness and diversity grow with model capability, suggesting that frontier LLMs may appear safe yet harbor increasingly dangerous knowledge beneath the alignment surface. Our source code is available at this https URL . Subjects: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI) Cite as: arXiv:2608.14577 [cs.CL] (or arXiv:2608.14577v1 [cs.CL] for this version) https://doi.org/10.48550/arXiv.2608.14577 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Zhouyuan Ma [ view email ] [v1] Thu, 11 Jun 2026 09:39:32 UTC (12,311 KB) Full-text links: Access Paper: View a PDF of the paper titled HarmProfile: Characterizing Harmful Distributions in Frontier LLMs, by Zhouyuan Ma and 8 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CL < prev | next > new | recent | 2026-08 Change to browse by: cs cs.AI 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? ) 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

• HarmProfile: Characterizing Harmful Distributions in Frontier LLMs#610079
• HarmProfile: Characterizing Harmful Distributions in Frontier LLMs#469471
• Safety in Self-Evolving LLM Agent Systems: Threats, Amplification, and Case Studies#299821
• The Oversight Gap: What LLM Safety Monitors Miss, and Why It Is Not Capability#975218
• Online Safety Monitoring for LLMs#332507