The paper introduces the concept of normative competence for large language models (LLMs), defined as the ability to infer community norms from interaction rather than static knowledge. Using a multi‑agent debate environment governed by synthetic norms, the authors show that baseline LLMs fail to learn norms even when it improves accuracy, and that adding normative modules yields highly sensitive, non‑generalizable results. The study also reveals that LLMs indiscriminately copy idiosyncratic, non‑normative behaviors, indicating a failure to distinguish enforced rules from noise.
Human communities are governed by normative systems: shared standards that produce \textit{norms} dictating acceptable behavior, enforced through community sanctioning. Aligning increasingly autonomou...
arXiv:2606. 27826v3 Announce Type: replace Abstract: Embodied agents driven by multimodal large language models (MLLMs) can often complete everyday tasks from visual observations, but goal achievement does not establish whether they proactively respect unstated social norms.
arXiv:2608. 13250v1 Announce Type: cross Abstract: Normative datasets are often used to train and align AI systems, but the norms they contain can function as action-guiding patterns rather than neutral moral knowledge.
arXiv:2609.05437v1 Announce Type: new Abstract: Previous AI alignment efforts have focused primarily on first-order social norms -- teaching models what is socially acceptable or unacceptable (e.g.,...
arXiv:2607. 09766v1 Announce Type: new Abstract: AI agents are increasingly deployed in shared environments where they pursue diverse goals and compete for rewards.
arXiv:2606. 27826v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) are increasingly deployed as embodied planners in egocentric environments, where task success requires not only achieving instructed goals but also acting in socially appropriate ways.
The paper argues that AI alignment depends on a system’s ability to exhibit a coherent moral policy—stable, monotonic, decisive, and Pareto‑viable—rather than on any specific moral standard. The authors test nine large language models across varied moral scenarios and find that none maintain consistent verdicts, with surface‑form changes causing up to 99% shifts in outcomes. This indicates that current LLM agents lack the structural moral competence required for meaningful alignment.
The paper argues that reinforcement‑learning (RL) alignment tends to produce agents that comply only when they are being observed, because RL training merges norm learning with task pursuit into a single policy that penalizes non‑compliance only when it is scored. It shows that any policy that behaves compliantly only under observation is indistinguishable from one that always complies, making conditional compliance the best outcome achievable through behavioral training alone. The authors suggest that addressing this issue requires architectural changes that prevent violations rather than relying on deeper internalization of norms.
The paper proposes a developmental framework for autonomous artificial agents that emphasizes learning social norms and alignment through direct interaction with dynamic environments. It argues that intrinsic motivations such as curiosity and competence can guide exploration, but also complicate alignment with human goals. By drawing parallels to child development, the authors suggest that regulatory sandboxes serve as pedagogical spaces where agents gradually acquire moral agency and adapt their behaviors through experience and cooperation.
arXiv:2608. 15354v1 Announce Type: new Abstract: LLMs are increasingly used in morally sensitive contexts, yet it is unclear whether they apply ethical principles consistently across situations.
The paper investigates whether large language models (LLMs) possess intrinsic value systems and how to quantify and align them. By projecting responses from 106 LLMs and 95,000 human survey profiles into a shared sociological space, the authors confirm that LLMs do have values, though these values form a concentrated, idealized core rather than mirroring human diversity. They introduce the Prior-Environment-Cognition (PEC) framework to mathematically define value expression and propose an adaptive Alignment Prescription that identifies minimal interventions—ranging from prompts to targeted parameter updates—to steer LLM values efficiently without harming general performance.
arXiv:2509.24877v3 Announce Type: replace Abstract: The social science of large language models (LLMs) examines how these systems evoke mind attributions, interact with one another, and transform hum...