arXiv AI
Aug 12
Toward a Theory of Value in AI Alignment
arXiv:2608. 10327v1 Announce Type: new Abstract: Can AI systems be aligned to human values?
Structuring the Space of Sociotechnical Alignment
arXiv:2607. 01250v1 Announce Type: cross Abstract: Sociotechnical alignment concerns the social desirability of AI behavior and is thus inherently normative, not merely technical.
Related stories
arXiv AI
Jun 24
Societal Alignment Frameworks Can Improve LLM Alignment
arXiv:2503. 00069v2 Announce Type: replace-cross Abstract: Recent progress in large language models (LLMs) has focused on producing responses that meet human expectations and align with shared values - a process coined alignment.
arXiv AI
Jun 29
The Alignment Target Problem: Divergent Moral Judgments of Humans, AI Systems, and Their Designers
arXiv:2604. 24155v3 Announce Type: replace-cross Abstract: The project of aligning machine behavior with human values raises a basic problem: whose moral expectations should guide AI decision-making?
arXiv AI
Sep 10
Beyond Right and Wrong: Evaluating Second-order Social Reasoning in Large Language Models
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 AI
Sep 10
The Emergence of Social Science of Large Language Models
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...
arXiv AI
Jun 15
Position: Align AI to Our Aspirations, Not Our Flaws
arXiv:2606. 13755v1 Announce Type: cross Abstract: We argue that aligning AI to aggregated human preferences is the wrong target.
arXiv AI
Jul 17
Align AI to Dynamic Human-AI Workflows
arXiv:2607. 14240v1 Announce Type: new Abstract: Current alignment approaches typically focus on emulating human behavior using static representations of human preferences, failing to capture the dynamic, context-dependent nature of real-world human-AI interactions.
arXiv Computation and Language
3d ago
Anthropomorphism in the age of Large Language Models: An overview of potential risks and mitigations
arXiv:2609.38486v1 Announce Type: cross Abstract: Large Language Models (LLMs) and more broadly Artificial Intelligence (AI) systems are often described and understood in human-like terms, a phenomen...
arXiv AI
Aug 5
Socially Grounded Agentic AI: Coordinating Plural Perspectives through Social Theory
arXiv:2608. 03910v1 Announce Type: new Abstract: As AI systems are deployed across increasingly diverse social contexts, alignment can no longer be framed as the optimization of a single, unified set of values.
arXiv AI
Sep 1
The Landscape of Generative AI in Information Systems: A Synthesis of Secondary Reviews and Research Agendas
The paper reviews secondary studies and research agendas on generative AI (GenAI) in information systems, synthesizing evidence from 28 selected papers. It identifies GenAI’s transformative benefits—productivity, innovation, personalization, and democratized expertise—while highlighting challenges such as technical unreliability, ethical risks, and governance gaps. The authors propose a research agenda that shifts IS scholarship toward shaping the co‑evolution of AI capabilities with organizational routines, societal values, and regulatory institutions, emphasizing hybrid human‑AI ensembles, situated validation, design principles for probabilistic systems, and adaptive governance.
arXiv AI
Aug 14
Position: The Alignment Community is Unintentionally Building a Censor's Toolkit
arXiv:2608. 12346v1 Announce Type: new Abstract: This position paper argues that modern AI alignment methods - originally designed to prevent harmful output - are dual-use technologies that may easily be misused by malicious actors for censorship and manipulation.
arXiv AI
Jun 9
Emergent alignment and the projectability of ethical personas
arXiv:2606. 09475v1 Announce Type: new Abstract: Work on `emergent misalignment' shows that finetuning LLMs on narrow tasks can induce broadly misaligned behavior.