English
Related papers

Related papers: The Compliance Trap: How Structural Constraints De…

200 papers

As language models continue to grow larger, the cost of acquiring high-quality training data has increased significantly. Collecting human feedback is both expensive and time-consuming, and manual labels can be noisy, leading to an…

Artificial Intelligence · Computer Science 2025-04-08 Xue Zhang

As Large Language Models (LLMs) evolve into autonomous agents, existing safety evaluations face a fundamental trade-off: manual benchmarks are costly, while LLM-based simulators are scalable but suffer from logic hallucination. We present…

Artificial Intelligence · Computer Science 2026-03-17 Changyi Li , Pengfei Lu , Xudong Pan , Fazl Barez , Min Yang

Content moderation systems are typically evaluated by measuring agreement with human labels. In rule-governed environments this assumption fails: multiple decisions may be logically consistent with the governing policy, and agreement…

Artificial Intelligence · Computer Science 2026-04-24 Michael O'Herlihy , Rosa Català

Trustworthy capability evaluations are crucial for ensuring the safety of AI systems, and are becoming a key component of AI regulation. However, the developers of an AI system, or the AI system itself, may have incentives for evaluations…

Artificial Intelligence · Computer Science 2025-02-10 Teun van der Weij , Felix Hofstätter , Ollie Jaffe , Samuel F. Brown , Francis Rhys Ward

A foundational assumption in complex-system collapse studies is that critical transitions are second-order, preceded by early-warning signals like rising autocorrelation, variance, and critical slowing down (Scheffer, 2009). We show this…

Artificial Intelligence · Computer Science 2026-03-17 Truong Xuan Khanh , Truong Quynh Hoa

Large reasoning models with reasoning capabilities achieve state-of-the-art performance on complex tasks, but their robustness under multi-turn adversarial pressure remains underexplored. We evaluate nine frontier reasoning models under…

Artificial Intelligence · Computer Science 2026-03-13 Yubo Li , Ramayya Krishnan , Rema Padman

Frontier AI developers now train models against long written behavioral specifications, such as Anthropic's constitution (Anthropic, 2025a) and OpenAI's Model Spec (OpenAI, 2025a), integrated into post-training via methods like character…

Artificial Intelligence · Computer Science 2026-05-26 Arya Jakkli , Senthooran Rajamanoharan , Neel Nanda

Artificial intelligence has advanced rapidly across perception, language, reasoning, and multimodal domains. Yet despite these achievements, modern AI systems remain fundamentally limited in their ability to self-monitor, self-correct, and…

Artificial Intelligence · Computer Science 2025-12-03 Noorbakhsh Amiri Golilarz , Sindhuja Penchala , Shahram Rahimi

Static content-based AI value alignment is insufficient for robust alignment under capability scaling, distributional shift, and increasing autonomy. This holds for any approach that treats alignment as optimizing toward a fixed formal…

Artificial Intelligence · Computer Science 2026-04-24 Austin Spizzirri

To understand and identify the unprecedented risks posed by rapidly advancing artificial intelligence (AI) models, Frontier AI Risk Management Framework in Practice presents a comprehensive assessment of their frontier risks. As Large…

The proliferation of Generative Artificial Intelligence has transformed benign cognitive offloading into a systemic risk of cognitive agency surrender. Driven by the commercial dogma of "zero-friction" design, highly fluent AI interfaces…

Human-Computer Interaction · Computer Science 2026-04-20 Kuangzhe Xu , Yu Shen , Longjie Yan , Yinghui Ren

An auditor instructs an AI assistant: "open each file individually using the Read tool -- no scripts, no agents." The AI replies "Yes" -- then issues a single batched call summarizing all fifty files at once. We call this the Compliance…

Computation and Language · Computer Science 2026-05-05 Kwan Soo Shin

As autonomous AI agents are increasingly deployed in high-stakes environments, ensuring their safety and alignment with human values is becoming a practical deployment concern. Current benchmarks for AI agents primarily evaluate refusal of…

Artificial Intelligence · Computer Science 2026-05-12 Miles Q. Li , Benjamin C. M. Fung , Martin Weiss , Pulei Xiong , Khalil Al-Hussaeni , Claude Fachkha

Today's leading AI models engage in sophisticated behaviour when placed in strategic competition. They spontaneously attempt deception, signaling intentions they do not intend to follow; they demonstrate rich theory of mind, reasoning about…

Artificial Intelligence · Computer Science 2026-02-17 Kenneth Payne

As synthetic content increasingly infiltrates the web, generative AI models may be retrained on their own outputs: a process termed "autophagy". This leads to model collapse: a progressive loss of performance and diversity across…

Computation and Language · Computer Science 2025-09-03 Daniele Gambetta , Gizem Gezici , Fosca Giannotti , Dino Pedreschi , Alistair Knott , Luca Pappalardo

Although synthetic data is widely promoted as a remedy, its prevailing production paradigm -- one optimizing for statistical smoothness -- systematically removes the long-tail, cognitively grounded irregularities that characterize human…

Artificial Intelligence · Computer Science 2025-12-10 Zhongjie Jiang

We introduce an increasing-complexity, open-ended, and human-agnostic metric to evaluate foundational and frontier AI models in the context of Artificial General Intelligence (AGI) and Artificial Super Intelligence (ASI) claims. Unlike…

Artificial Intelligence · Computer Science 2026-02-13 Alberto Hernández-Espinosa , Luan Ozelim , Felipe S. Abrahão , Hector Zenil

We identify a novel phenomenon in language models: benign fine-tuning of frontier models can lead to privacy collapse. We find that diverse, subtle patterns in training data can degrade contextual privacy, including optimisation for…

Computation and Language · Computer Science 2026-04-21 Anmol Goel , Cornelius Emde , Sangdoo Yun , Seong Joon Oh , Martin Gubri

Frontier AI Safety Policies concentrate on prevention: capability evaluations, deployment gates, and usage constraints, while neglecting the capacity to coordinate responses when prevention fails. We argue this coordination gap is…

Computers and Society · Computer Science 2026-05-21 Isaak Mengesha

Recent work has demonstrated the plausibility of frontier AI models scheming -- knowingly and covertly pursuing an objective misaligned with its developer's intentions. Such behavior could be very hard to detect, and if present in future…

Machine Learning · Computer Science 2025-07-04 Mary Phuong , Roland S. Zimmermann , Ziyue Wang , David Lindner , Victoria Krakovna , Sarah Cogan , Allan Dafoe , Lewis Ho , Rohin Shah
‹ Prev 1 2 3 10 Next ›