AI Safety & Ethics

Alignment, bias, regulation, and responsible AI

This Week's Best | Monthly Best | Guide | Trending

Top This Week

[2601.15356] Q-Probe: Scaling Image Quality Assessment to High Resolution via Context-Aware Agentic Probing
Llms

[2601.15356] Q-Probe: Scaling Image Quality Assessment to High Resolution via Context-Aware Agentic Probing

Abstract page for arXiv paper 2601.15356: Q-Probe: Scaling Image Quality Assessment to High Resolution via Context-Aware Agentic Probing

arXiv - AI · 4 min ·
[2510.18196] Contrastive Decoding Mitigates Score Range Bias in LLM-as-a-Judge
Llms

[2510.18196] Contrastive Decoding Mitigates Score Range Bias in LLM-as-a-Judge

Abstract page for arXiv paper 2510.18196: Contrastive Decoding Mitigates Score Range Bias in LLM-as-a-Judge

arXiv - AI · 3 min ·
[2509.23435] AudioRole: An Audio Dataset for Character Role-Playing in Large Language Models
Llms

[2509.23435] AudioRole: An Audio Dataset for Character Role-Playing in Large Language Models

Abstract page for arXiv paper 2509.23435: AudioRole: An Audio Dataset for Character Role-Playing in Large Language Models

arXiv - AI · 4 min ·

All Content

[2510.07117] The Conditions of Physical Embodiment Enable Generalization and Care
Ai Agents

[2510.07117] The Conditions of Physical Embodiment Enable Generalization and Care

This paper explores how physical embodiment in artificial agents can enhance their ability to generalize and provide care in uncertain en...

arXiv - Machine Learning · 4 min ·
[2510.00664] Batch-CAM: Introduction to better reasoning in convolutional deep learning models
Machine Learning

[2510.00664] Batch-CAM: Introduction to better reasoning in convolutional deep learning models

The paper introduces Batch-CAM, a training framework for convolutional deep learning models that enhances interpretability by aligning mo...

arXiv - AI · 4 min ·
[2507.19593] A Survey on Hypergame Theory: Modeling Misaligned Perceptions and Nested Beliefs for Multi-agent Systems
Machine Learning

[2507.19593] A Survey on Hypergame Theory: Modeling Misaligned Perceptions and Nested Beliefs for Multi-agent Systems

This article surveys hypergame theory, focusing on modeling misaligned perceptions and nested beliefs in multi-agent systems, highlightin...

arXiv - AI · 4 min ·
[2501.05454] The Epistemic Asymmetry of Consciousness Self-Reports: A Formal Analysis of AI Consciousness Denial
Ai Safety

[2501.05454] The Epistemic Asymmetry of Consciousness Self-Reports: A Formal Analysis of AI Consciousness Denial

This article presents a formal analysis of AI consciousness denial, revealing that self-reports of consciousness by AI systems are episte...

arXiv - AI · 4 min ·
[2602.13156] In-Context Autonomous Network Incident Response: An End-to-End Large Language Model Agent Approach
Llms

[2602.13156] In-Context Autonomous Network Incident Response: An End-to-End Large Language Model Agent Approach

This article presents a novel approach to network incident response using a large language model (LLM) that autonomously learns and adapt...

arXiv - AI · 4 min ·
[2602.13110] SCOPE: Selective Conformal Optimized Pairwise LLM Judging
Llms

[2602.13110] SCOPE: Selective Conformal Optimized Pairwise LLM Judging

The paper presents SCOPE, a framework for selective pairwise evaluation using large language models (LLMs) that improves judgment accurac...

arXiv - AI · 4 min ·
[2602.13088] How cyborg propaganda reshapes collective action
Computer Vision

[2602.13088] How cyborg propaganda reshapes collective action

This paper explores the emergence of 'cyborg propaganda,' where human and AI collaboration reshapes collective action, blurring lines bet...

arXiv - AI · 4 min ·
[2602.13087] EXCODER: EXplainable Classification Of DiscretE time series Representations
Machine Learning

[2602.13087] EXCODER: EXplainable Classification Of DiscretE time series Representations

The paper explores EXCODER, a method for explainable classification of discrete time series representations, enhancing interpretability w...

arXiv - Machine Learning · 4 min ·
[2602.13061] Diverging Flows: Detecting Extrapolations in Conditional Generation
Machine Learning

[2602.13061] Diverging Flows: Detecting Extrapolations in Conditional Generation

The paper introduces Diverging Flows, a method for detecting extrapolations in conditional generation models, enhancing safety in applica...

arXiv - Machine Learning · 3 min ·
[2602.13055] Curriculum-DPO++: Direct Preference Optimization via Data and Model Curricula for Text-to-Image Generation
Machine Learning

[2602.13055] Curriculum-DPO++: Direct Preference Optimization via Data and Model Curricula for Text-to-Image Generation

The paper presents Curriculum-DPO++, an advanced method for text-to-image generation that optimizes preference learning through a dual cu...

arXiv - Machine Learning · 4 min ·
[2602.13047] Can we trust AI to detect healthy multilingual English speakers among the cognitively impaired cohort in the UK? An investigation using real-world conversational speech
Machine Learning

[2602.13047] Can we trust AI to detect healthy multilingual English speakers among the cognitively impaired cohort in the UK? An investigation using real-world conversational speech

This study investigates the reliability of AI in detecting cognitive impairment among multilingual English speakers in the UK, revealing ...

arXiv - AI · 4 min ·
[2602.13033] Buy versus Build an LLM: A Decision Framework for Governments
Llms

[2602.13033] Buy versus Build an LLM: A Decision Framework for Governments

This paper presents a strategic framework for governments to decide between buying or building large language models (LLMs) for public se...

arXiv - AI · 4 min ·
[2602.13017] Synaptic Activation and Dual Liquid Dynamics for Interpretable Bio-Inspired Models
Machine Learning

[2602.13017] Synaptic Activation and Dual Liquid Dynamics for Interpretable Bio-Inspired Models

This paper presents a unified framework for bio-inspired models that enhances interpretability in recurrent neural networks (RNNs) throug...

arXiv - Machine Learning · 3 min ·
[2602.12983] Detecting Object Tracking Failure via Sequential Hypothesis Testing
Machine Learning

[2602.12983] Detecting Object Tracking Failure via Sequential Hypothesis Testing

This paper presents a method for detecting object tracking failures using sequential hypothesis testing, enhancing safety in computer vis...

arXiv - AI · 4 min ·
[2602.12975] Extending confidence calibration to generalised measures of variation
Machine Learning

[2602.12975] Extending confidence calibration to generalised measures of variation

The paper introduces the Variation Calibration Error (VCE) metric, extending confidence calibration methods in machine learning to assess...

arXiv - Machine Learning · 3 min ·
[2602.12968] RGAlign-Rec: Ranking-Guided Alignment for Latent Query Reasoning in Recommendation Systems
Llms

[2602.12968] RGAlign-Rec: Ranking-Guided Alignment for Latent Query Reasoning in Recommendation Systems

The RGAlign-Rec framework enhances proactive intent prediction in e-commerce chatbots by aligning latent query reasoning with ranking obj...

arXiv - AI · 4 min ·
[2602.12917] Ultrasound-Guided Real-Time Spinal Motion Visualization for Spinal Instability Assessment
Data Science

[2602.12917] Ultrasound-Guided Real-Time Spinal Motion Visualization for Spinal Instability Assessment

This article presents a novel ultrasound-guided method for real-time 3D visualization of spinal motion to assess spinal instability, aimi...

arXiv - AI · 4 min ·
[2602.12902] Robustness of Object Detection of Autonomous Vehicles in Adverse Weather Conditions
Machine Learning

[2602.12902] Robustness of Object Detection of Autonomous Vehicles in Adverse Weather Conditions

This paper evaluates the robustness of object detection models used in autonomous vehicles under adverse weather conditions, proposing a ...

arXiv - Machine Learning · 4 min ·
[2602.12892] RADAR: Revealing Asymmetric Development of Abilities in MLLM Pre-training
Llms

[2602.12892] RADAR: Revealing Asymmetric Development of Abilities in MLLM Pre-training

The paper presents RADAR, a novel evaluation framework for Multi-modal Large Language Models (MLLMs) that addresses performance bottlenec...

arXiv - AI · 4 min ·
[2602.12873] Knowledge-Based Design Requirements for Generative Social Robots in Higher Education
Llms

[2602.12873] Knowledge-Based Design Requirements for Generative Social Robots in Higher Education

The article explores design requirements for generative social robots in higher education, emphasizing the need for knowledge-based frame...

arXiv - AI · 3 min ·
Previous Page 122 Next

Related Topics

Machine Learning Large Language Models Generative AI Natural Language Processing Computer Vision Robotics & Embodied AI

Stay updated with AI News

Get the latest news, tools, and insights delivered to your inbox.

Subscribe to Newsletter

Daily or weekly digest • Unsubscribe anytime