English
Related papers

Related papers: The Alignment Trap: Complexity Barriers

200 papers

We prove that platform-deterministic inference is necessary and sufficient for trustworthy AI. We formalize this as the Determinism Thesis and introduce trust entropy to quantify the cost of non-determinism, proving that verification…

Artificial Intelligence · Computer Science 2026-03-27 TJ Dunham

The project of aligning machine behavior with human values raises a basic problem: whose moral expectations should guide AI decision-making? Much alignment research assumes that the appropriate benchmark is how humans themselves would act…

Computers and Society · Computer Science 2026-05-13 Benjamin Minhao Chen , Xinyu Xie

Safety frameworks represent a significant development in AI governance: they are the first type of publicly shared catastrophic risk management framework developed by major AI companies and focus specifically on AI scaling decisions. I…

Computers and Society · Computer Science 2024-10-02 Atoosa Kasirzadeh

Coalition Logic is primarily concerned with what coalitions can achieve, whereas what coalitions cannot achieve -- their \emph{inability} -- has received comparatively little explicit attention. This asymmetry matters in artificial…

Logic in Computer Science · Computer Science 2026-05-01 Shanxia Wang

As large-scale language models increasingly impact safety-critical domains, ensuring their reliable adherence to well-defined principles remains a fundamental challenge. We introduce Deliberative Alignment, a new paradigm that directly…

Productive human-AI collaboration requires appropriate reliance, yet contemporary AI systems are often miscalibrated, exhibiting systematic overconfidence or underconfidence. We investigate whether humans can learn to mentally recalibrate…

Human-Computer Interaction · Computer Science 2026-03-25 ZhaoBin Li , Mark Steyvers

Understanding convergent learning -- the degree to which independently trained neural systems -- whether multiple artificial networks or brains and models -- arrive at similar internal representations -- is crucial for both neuroscience and…

Neurons and Cognition · Quantitative Biology 2026-01-26 Chaitanya Kapoor , Sudhanshu Srivastava , Meenakshi Khosla

Machine learning (ML) systems are rapidly increasing in size, are acquiring new capabilities, and are increasingly deployed in high-stakes settings. As with other powerful technologies, safety for ML should be a leading research priority.…

Machine Learning · Computer Science 2022-06-20 Dan Hendrycks , Nicholas Carlini , John Schulman , Jacob Steinhardt

Safety alignment is a key requirement for building reliable Artificial General Intelligence. Despite significant advances in safety alignment, we observe that minor latent shifts can still trigger unsafe responses in aligned models. We…

Machine Learning · Computer Science 2025-06-23 Tianle Gu , Kexin Huang , Zongqi Wang , Yixu Wang , Jie Li , Yuanqi Yao , Yang Yao , Yujiu Yang , Yan Teng , Yingchun Wang

Technical and legal debates frequently suggest that "accuracy" is an objective, measurable, and purely technical property. We challenge this view, showing that evaluating AI performance fundamentally depends on context-dependent normative…

Computers and Society · Computer Science 2026-04-29 Lucas G. Uberti-Bona Marin , Bram Rijsbosch , Kristof Meding , Gerasimos Spanakis , Gijs van Dijck , Konrad Kollnig

Symmetries play a central role in physics, organizing dynamics, constraining interactions, and determining the effective number of physical degrees of freedom. In parallel, modern artificial intelligence methods have demonstrated a…

High Energy Physics - Phenomenology · Physics 2026-02-03 Veronica Sanz

As Large Language Models (LLMs) become increasingly integrated into real-world decision-making systems, understanding their behavioural vulnerabilities remains a critical challenge for AI safety and alignment. While existing evaluation…

Artificial Intelligence · Computer Science 2025-05-20 Lili Zhang , Haomiaomiao Wang , Long Cheng , Libao Deng , Tomas Ward

The emergence of multi-agent systems built from large language models (LLMs) offers a promising paradigm for scalable collective intelligence and self-evolution. Ideally, such systems would achieve continuous self-improvement in a fully…

Computation and Language · Computer Science 2026-02-12 Chenxu Wang , Chaozhuo Li , Songyang Liu , Zejian Chen , Jinyu Hou , Ji Qi , Rui Li , Litian Zhang , Qiwei Ye , Zheng Liu , Xu Chen , Xi Zhang , Philip S. Yu

AI development has a fiction dependency problem: models are built on massive corpora of modern fiction and desperately need more of it, yet they struggle to generate it. I term this the AI-Fiction Paradox and it is particularly startling…

Artificial Intelligence · Computer Science 2026-03-17 Katherine Elkins

Despite productivity increasing eightfold since Keynes's 1930 prediction of 15-hour workweeks, workers globally still work roughly double these hours. Separately, AI development accelerates despite existential risk warnings from leading…

Computers and Society · Computer Science 2025-12-30 Ali Dasdan

Objective: This paper develops a theoretical framework explaining when and why AI explanations enhance versus impair human decision-making. Background: Transparency is advocated as universally beneficial for human-AI interaction, yet…

Human-Computer Interaction · Computer Science 2026-01-21 Ancuta Margondai , Mustapha Mouloua

Legal theory can address two related key problems of alignment: pluralism and specification. Alignment researchers must determine how to specify what is concretely meant by vague principles like helpfulness and fairness and they must ensure…

Computers and Society · Computer Science 2024-10-29 Nicholas A. Caputo

The ubiquity of Large Language Models (LLMs) is driving a paradigm shift where user convenience supersedes computational efficiency. This article defines the "Plausibility Trap": a phenomenon where individuals with access to Artificial…

Artificial Intelligence · Computer Science 2026-01-22 Ivan Carrera , Daniel Maldonado-Ruiz

As artificial intelligence assumes cognitive labor, no quantitative framework predicts when human capability loss becomes catastrophic. We present a two-variable dynamical systems model coupling capability (H) and delegation (D), grounded…

Computers and Society · Computer Science 2026-03-26 Jeongju Park , Musu Kim , Sekyung Han

The integration of Large Language Models (LLMs) into software engineering has revolutionized code generation, enabling unprecedented productivity through promptware and autonomous AI agents. However, this transformation introduces…

Software Engineering · Computer Science 2025-08-19 Satyam Kumar Navneet , Joydeep Chandra