Position: Anthropomorphic Misalignment Research Needs Stronger Evidence

We argue that many Anthropomorphic Misalignment Research (AMR) studies need stronger evidence to ensure that they can provide a robust foundation for critical safety decisions, such as model deployment and regulation. By evaluating failure modes across different misalignment concepts, such as deception, emergent misalignment, and sycophancy, we show how conceptual ambiguity, non-robust datasets, experimental design, and insufficient causal interventions can lead to overinterpretation of model behaviors. This position paper aims to offer guidance on evidentiary considerations that can help improve methodological rigor in AMR. To achieve this, we provide a clear call to action through a proposed framework of evidence levels and a diagnostic checklist. These shared standards will enable more productive scientific discourse and ensure that claims about AI risks rest on solid empirical foundations.

Introduction. Can I trust my AI assistant? This question becomes increasingly relevant with the rapid adoption of large language models (LLMs) and artificial intelligence (AI) agents. Recently, AI systems have advanced significantly in terms of capability and general “intelligence”, which is also reflected in the nature of their failure modes. Many frontier models display eerie “human-like” failure modes, including behaviors that resemble deceptionÛ (Park et al., 2024), schemingÛ (Meinke et al., 2024), instrumental goals (Ward et al., 2024), and more (Sharma et al., 2024; Laine et al., 2024; Schlatter et al., 2026). We refer to such failures as instances of anthropomorphic misalignment. Deploying advanced AI that exhibits anthropomorphic misalignment in high-stakes environments could have catas- trophic consequences, such as power-seekingÛ (Carlsmith, 2022) or loss of controlÛ (Bostrom, 2014; Turchin & Denkenberger, 2020).

Discussion / Conclusion. The study of anthropomorphic misalignment remains a vital pillar of AI safety, offering insights into how complex models might behave in high-stakes environments. The challenges and recommendations discussed aim not to diminish this research but to strengthen its scientific foundation. By shifting the field’s focus towards more precise target framing, diverse data construction, robust experimental design, and rigorous causal-mechanistic attribution, observations of model behavior can be grounded in reproducible and technically sound evidence. As the community moves from exploratory, pre-paradigmatic behavioral studies toward a more mature, solid science of alignment, these standards will help ensure evaluations provide the technical clarity necessary to effectively inform researchers, developers, and policymakers regarding decisions around serious AI risks.