English
Related papers

Related papers: Foveate, Attribute, and Rationalize: Towards Physi…

200 papers

Reinforcement learning (RL) is ubiquitous in the development of modern AI systems. However, state-of-the-art RL agents require extensive, and potentially unsafe, interactions with their environments to learn effectively. These limitations…

Machine Learning · Computer Science 2025-08-01 Yarden As , Bhavya Sukhija , Lenart Treven , Carmelo Sferrazza , Stelian Coros , Andreas Krause

As large reasoning models (LRMs) grow more capable, chain-of-thought (CoT) reasoning introduces new safety challenges. Existing SFT-based safety alignment studies dominantly focused on filtering prompts with safe, high-quality responses,…

Computation and Language · Computer Science 2026-03-31 Raj Vardhan Tomar , Preslav Nakov , Yuxia Wang

In a world where traditional notions of privacy are increasingly challenged by the myriad companies that collect and analyze our data, it is important that decision-making entities are held accountable for unfair treatments arising from…

Computers and Society · Computer Science 2016-08-17 Florian Tramèr , Vaggelis Atlidakis , Roxana Geambasu , Daniel Hsu , Jean-Pierre Hubaux , Mathias Humbert , Ari Juels , Huang Lin

Safety cases - clear, assessable arguments for the safety of a system in a given context - are a widely-used technique across various industries for showing a decision-maker (e.g. boards, customers, third parties) that a system is safe. In…

Computers and Society · Computer Science 2025-03-10 Benjamin Hilton , Marie Davidsen Buhl , Tomek Korbak , Geoffrey Irving

RAG systems have transformed how LLMs access external knowledge, but we find that current implementations exhibit a bias toward factual, objective content, as evidenced by existing benchmarks and datasets that prioritize objective…

Artificial Intelligence · Computer Science 2026-04-15 Aditya Agrawal , Alwarappan Nakkiran , Darshan Fofadiya , Alex Karlsson , Harsha Aduri

While the increased use of AI in the manufacturing sector has been widely noted, there is little understanding on the risks that it may raise in a manufacturing organisation. Although various high level frameworks and definitions have been…

Artificial Intelligence · Computer Science 2025-12-17 Alexandra Brintrup , George Baryannis , Ashutosh Tiwari , Svetan Ratchev , Giovanna Martinez-Arellano , Jatinder Singh

This report examines a novel risk associated with current (and projected) AI tools. Making effective decisions about future actions requires us to reason under uncertainty (RUU), and doing so is essential to many critical real world…

Computers and Society · Computer Science 2024-02-06 Toby D. Pilditch

Explainability and Safety engender Trust. These require a model to exhibit consistency and reliability. To achieve these, it is necessary to use and analyze data and knowledge with statistical and symbolic AI methods relevant to the AI…

Artificial Intelligence · Computer Science 2023-12-13 Manas Gaur , Amit Sheth

Early design decisions strongly influence environmental, economic and social outcomes, yet sustainability assessment tools rarely reveal trade-offs among these three pillars. This study presents a framework for Conflict Mapping and…

Physics and Society · Physics 2025-12-15 Apala Chakrabarti

When AI systems are granted the agency to take impactful actions in the real world, there is an inherent risk that these systems behave in ways that are harmful. Typically, humans specify constraints on the AI system to prevent harmful…

Human-Computer Interaction · Computer Science 2022-11-09 Travis Mandel , Jahnu Best , Randall H. Tanaka , Hiram Temple , Chansen Haili , Kayla Schlectinger , Roy Szeto

Despite being able to generate fluent and grammatical text, current Seq2Seq summarization models still suffering from the unfaithful generation problem. In this paper, we study the faithfulness of existing systems from a new perspective of…

Computation and Language · Computer Science 2022-11-02 Wenhao Wu , Wei Li , Jiachen Liu , Xinyan Xiao , Ziqiang Cao , Sujian Li , Hua Wu

Black box neural networks are an indispensable part of modern robots. Nevertheless, deploying such high-stakes systems in real-world scenarios poses significant challenges when the stakeholders, such as engineers and legislative bodies,…

Robotics · Computer Science 2025-10-10 Som Sagar , Aditya Taparia , Harsh Mankodiya , Pranav Bidare , Yifan Zhou , Ransalu Senanayake

Effectiveness and interpretability are two essential properties for trustworthy AI systems. Most recent studies in visual reasoning are dedicated to improving the accuracy of predicted answers, and less attention is paid to explaining the…

Computer Vision and Pattern Recognition · Computer Science 2022-03-14 Shi Chen , Qi Zhao

Security evaluations inherently depend on stable identifiers. Any finding, audit, or regulatory decision must remain attached to the specific artifact it pertains to. Continuously updated artificial intelligence systems violate this core…

Cryptography and Security · Computer Science 2026-05-26 Dan Ristea , Vasilios Mavroudis

In today's world, with the rise of numerous social platforms, it has become relatively easy for anyone to spread false information and lure people into traps. Fraudulent schemes and traps are growing rapidly in the investment world. Due to…

Artificial Intelligence · Computer Science 2023-08-23 Prabh Simran Singh Baweja , Orathai Sangpetch , Akkarit Sangpetch

Currently, the dominant paradigm in AI safety is alignment with human values. Here we describe progress on developing an alternative approach to safety, based on ethical rationalism (Gewirth:1978), and propose an inherently safe…

Artificial Intelligence · Computer Science 2023-03-21 András Kornai , Michael Bukatin , Zsolt Zombori

The demand for accurate and efficient verification of information in texts generated by large language models (LMs) is at an all-time high, but remains unresolved. Recent efforts have focused on extracting and verifying atomic facts from…

Computation and Language · Computer Science 2024-09-25 Vasileios Katranidis , Gabor Barany

Interpretability has become an essential topic for artificial intelligence in some high-risk domains such as healthcare, bank and security. For commonly-used tabular data, traditional methods trained end-to-end machine learning models with…

Artificial Intelligence · Computer Science 2022-08-18 Haixiao Chi , Dawei Wang , Gaojie Cui , Feng Mao , Beishui Liao

Recent work has highlighted the importance of monitoring chain-of-thought reasoning for AI safety; however, current approaches that analyze textual reasoning steps can miss subtle harmful patterns and may be circumvented by models that hide…

Artificial Intelligence · Computer Science 2025-10-22 Antonio-Gabriel Chacón Menke , Phan Xuan Tan , Eiji Kamioka

Recent research shows -- somewhat astonishingly -- that people are willing to ascribe moral blame to AI-driven systems when they cause harm [1]-[4]. In this paper, we explore the moral-psychological underpinnings of these findings. Our…

Human-Computer Interaction · Computer Science 2021-02-10 Markus Kneer , Michael T. Stuart
‹ Prev 1 3 4 5 6 7 10 Next ›