Muse Spark Safety & Preparedness Report

• URL: http://arxiv.org/abs/2606.12429v1
• Date: Thu, 14 May 2026 23:12:14 GMT
• Title: Muse Spark Safety & Preparedness Report
• Abstract summary: Muse Spark is the latest large language model developed by Meta.<n>We first present evaluations for catastrophic risk domains under Meta's Advanced AI Scaling Framework.<n>We then discuss additional considerations, such as Muse Spark's broader content safety and behavioral profile.
• Score: 106.21435337776768
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Muse Spark is the latest large language model developed by Meta. In this report, we first present evaluations for catastrophic risk domains under Meta's Advanced AI Scaling Framework, along with the evidence that informed our launch decision. We then discuss additional considerations, such as Muse Spark's broader content safety and behavioral profile, that are relevant to overall safety but fall outside the catastrophic risk domains governed by the Framework. Our preparedness results covering Chemical and Biological, Cybersecurity, and Loss of Control risks assess Muse Spark's deployment within Meta AI as presenting acceptable levels of residual risks under our Advanced AI Scaling Framework. We conducted a broad set of evaluations targeting dual-use and high-risk capabilities across these catastrophic risk domains. Those evaluations identified elevated risks prior to mitigations, with Chemical and Biological capabilities assessed as likely reaching the "high risk" category under the Advanced AI Scaling Framework before safeguards were applied. We have implemented a multi-layered set of mitigations that address the identified risks, and Muse Spark demonstrates state-of-the-art refusal across a range of benchmarks related to hazardous workflows in chemistry and biology. We therefore release Muse Spark as the underlying model of Meta AI.

Related papers

• Emergent Strategic Reasoning Risks in AI: A Taxonomy-Driven Evaluation Framework [63.74295981594549]
  Large language models (LLMs) engage in behaviors that serve their own objectives.<n>These include, but are not limited to, deception (intentionally misleading users or evaluators), evaluation gaming (strategically manipulating performance during safety testing), and reward hacking.<n>We introduce ESRRSim, a taxonomy-driven agentic framework for automated behavioral risk evaluation.
  arXiv  Detail & Related papers  (2026-04-23T23:44:01Z)
• ForesightSafety Bench: A Frontier Risk Evaluation and Governance Framework towards Safe AI [38.70363180741332]
  "ForesightSafety Bench" is a safety evaluation framework for cutting-edge AI models.<n>The benchmark has accumulated tens of thousands of structured risk data points and assessment results.<n>Based on this benchmark, we conduct systematic evaluation and in-depth analysis of over twenty mainstream advanced large models.
  arXiv  Detail & Related papers  (2026-02-15T13:12:44Z)
• The Shadow Self: Intrinsic Value Misalignment in Large Language Model Agents [37.75212140218036]
  We formalize the Loss-of-Control risk and identify the previously underexamined Intrinsic Value Misalignment (Intrinsic VM)<n>We then introduce IMPRESS, a scenario-driven framework for systematically assessing this risk.<n>We evaluate Intrinsic VM on 21 state-of-the-art LLM agents and find that it is a common and broadly observed safety risk across models.
  arXiv  Detail & Related papers  (2026-01-24T07:09:50Z)
• Toward Quantitative Modeling of Cybersecurity Risks Due to AI Misuse [50.87630846876635]
  We develop nine detailed cyber risk models.<n>Each model decomposes attacks into steps using the MITRE ATT&CK framework.<n>Individual estimates are aggregated through Monte Carlo simulation.
  arXiv  Detail & Related papers  (2025-12-09T17:54:17Z)
• The Role of Risk Modeling in Advanced AI Risk Management [33.357295564462284]
  Rapidly advancing artificial intelligence (AI) systems introduce novel, uncertain, and potentially catastrophic risks.<n>Managing these risks requires a mature risk-management infrastructure whose cornerstone is rigorous risk modeling.<n>We argue that advanced-AI governance should adopt a similar dual approach and that verifiable, provably-safe AI architectures are urgently needed.
  arXiv  Detail & Related papers  (2025-12-09T15:37:33Z)
• SafeRBench: A Comprehensive Benchmark for Safety Assessment in Large Reasoning Models [60.8821834954637]
  We present SafeRBench, the first benchmark that assesses LRM safety end-to-end.<n>We pioneer the incorporation of risk categories and levels into input design.<n>We introduce a micro-thought chunking mechanism to segment long reasoning traces into semantically coherent units.
  arXiv  Detail & Related papers  (2025-11-19T06:46:33Z)
• SafeBench: A Safety Evaluation Framework for Multimodal Large Language Models [75.67623347512368]
  We propose toolns, a comprehensive framework designed for conducting safety evaluations of MLLMs. Our framework consists of a comprehensive harmful query dataset and an automated evaluation protocol. Based on our framework, we conducted large-scale experiments on 15 widely-used open-source MLLMs and 6 commercial MLLMs.
  arXiv  Detail & Related papers  (2024-10-24T17:14:40Z)
• EARBench: Towards Evaluating Physical Risk Awareness for Task Planning of Foundation Model-based Embodied AI Agents [53.717918131568936]
  Embodied artificial intelligence (EAI) integrates advanced AI models into physical entities for real-world interaction.<n>Foundation models as the "brain" of EAI agents for high-level task planning have shown promising results.<n>However, the deployment of these agents in physical environments presents significant safety challenges.<n>This study introduces EARBench, a novel framework for automated physical risk assessment in EAI scenarios.
  arXiv  Detail & Related papers  (2024-08-08T13:19:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.