English
Related papers

Related papers: How Should AI Safety Benchmarks Benchmark Safety?

200 papers

The field of AI safety seeks to prevent or reduce the harms caused by AI systems. A simple and appealing account of what is distinctive of AI safety as a field holds that this feature is constitutive: a research project falls within the…

Computers and Society · Computer Science 2025-05-06 Jacqueline Harding , Cameron Domenico Kirk-Giannini

Benchmarks are essential for unified evaluation and reproducibility. The rapid rise of Artificial Intelligence for Software Engineering (AI4SE) has produced numerous benchmarks for tasks such as code generation and bug repair. However, this…

Software Engineering · Computer Science 2025-12-15 Roham Koohestani , Philippe de Bekker , Begüm Koç , Maliheh Izadi

As AI systems become more advanced, concerns about large-scale risks from misuse or accidents have grown. This report analyzes the technical research into safe AI development being conducted by three leading AI companies: Anthropic, Google…

Computers and Society · Computer Science 2024-09-26 Oscar Delaney , Oliver Guest , Zoe Williams

Artificial Intelligence (AI) is becoming the corner stone of many systems used in our daily lives such as autonomous vehicles, healthcare systems, and unmanned aircraft systems. Machine Learning is a field of AI that enables systems to…

Artificial Intelligence · Computer Science 2022-06-27 Lionel Nganyewou Tidjon , Foutse Khomh

As Artificial Intelligence (AI) systems become increasingly integrated into various aspects of daily life, concerns about privacy and ethical accountability are gaining prominence. This study explores stakeholder perspectives on privacy in…

Computers and Society · Computer Science 2025-03-18 Ajay Kumar Shrestha , Sandhya Joshi

Rapid progress in machine learning and artificial intelligence (AI) has brought increasing attention to the potential impacts of AI technologies on society. In this paper we discuss one such potential impact: the problem of accidents in…

Artificial Intelligence · Computer Science 2016-07-26 Dario Amodei , Chris Olah , Jacob Steinhardt , Paul Christiano , John Schulman , Dan Mané

Large language model-based agents are rapidly evolving from simple conversational assistants into autonomous systems capable of performing complex, professional-level tasks in various domains. While these advancements promise significant…

When AI interacts with the physical world -- as a robot or an assistive agent -- new safety challenges emerge beyond those of purely ``digital AI". In such interactions, the potential for physical harm is direct and immediate. How well do…

AI safety is still largely framed as alignment: training models to follow human preferences, safety policies, and normative constraints. That framing has improved the behavior of modern language models, but aligned behavior does not by…

Artificial Intelligence · Computer Science 2026-05-27 Yige Li , Yunhao Feng , Jun Sun

This paper addresses the question of how to align AI systems with human values and situates it within a wider body of thought regarding technology and value. Far from existing in a vacuum, there has long been an interest in the ability of…

Computers and Society · Computer Science 2021-01-19 Iason Gabriel , Vafa Ghazavi

Artificial intelligence (AI) is reshaping society, from video generation to medical diagnosis, coding agents to autonomous vehicles. Yet researchers, policymakers, and technology companies lack shared terminology for discussing AI risks.…

AI agents have been boosted by large language models. AI agents can function as intelligent assistants and complete tasks on behalf of their users with access to tools and the ability to execute commands in their environments. Through…

Cryptography and Security · Computer Science 2024-12-19 Yifeng He , Ethan Wang , Yuyang Rong , Zifei Cheng , Hao Chen

Artificial Intelligence (AI) Safety Institutes and governments worldwide are deciding whether they evaluate advanced AI themselves, support a private evaluation ecosystem or do both. Evaluation regimes have been established in a wide range…

Computers and Society · Computer Science 2025-08-06 Merlin Stein , Milan Gandhi , Theresa Kriecherbauer , Amin Oueslati , Robert Trager

Auditing plays a pivotal role in the development of trustworthy AI. However, current research primarily focuses on creating auditable AI documentation, which is intended for regulators and experts rather than end-users affected by AI…

Computers and Society · Computer Science 2023-05-31 Nicolas Scharowski , Michaela Benk , Swen J. Kühne , Léane Wettstein , Florian Brühlmann

Large language models are rapidly being deployed as AI tutors, yet current evaluation paradigms assess problem-solving accuracy and generic safety in isolation, failing to capture whether a model is simultaneously pedagogically effective…

Computation and Language · Computer Science 2026-03-19 Rima Hazra , Bikram Ghuku , Ilona Marchenko , Yaroslava Tokarieva , Sayan Layek , Somnath Banerjee , Julia Stoyanovich , Mykola Pechenizkiy

AI advancements have been significantly driven by a combination of foundation models and curiosity-driven learning aimed at increasing capability and adaptability. Within this landscape, open-endedness, where AI agents autonomously and…

Artificial Intelligence · Computer Science 2026-05-06 Ivaxi Sheth , Jan Wehner , Sahar Abdelnabi , Ruta Binkyte , Mario Fritz

We present a quantitative model for tracking dangerous AI capabilities over time. Our goal is to help the policy and research community visualise how dangerous capability testing can give us an early warning about approaching AI risks. We…

Artificial Intelligence · Computer Science 2024-12-23 Paolo Bova , Alessandro Di Stefano , The Anh Han

As AI models are increasingly deployed across diverse real-world scenarios, ensuring their safety remains a critical yet underexplored challenge. While substantial efforts have been made to evaluate and enhance AI safety, the lack of a…

There is a tendency across different subfields in AI to valorize a small collection of influential benchmarks. These benchmarks operate as stand-ins for a range of anointed common problems that are frequently framed as foundational…

Machine Learning · Computer Science 2021-12-01 Inioluwa Deborah Raji , Emily M. Bender , Amandalynne Paullada , Emily Denton , Alex Hanna