Artificial Intelligence & Ethics

Global: Study Shows LLMs Can Infer Private User Attributes from Facebook AdsA new study released on arXiv in September 2025 demonstrates that large language models can deduce personal characteristics such…

Global: Guided Perturbation Sensitivity Detects Adversarial Text with High AccuracyA new detection framework called Guided Perturbation Sensitivity (GPS) has been presented by researchers to identify adversarially modified text inputs. The…

Global: Study Reveals Geolocation Privacy Risks in Multi-Modal Large Reasoning ModelsA recent arXiv preprint introduces a privacy risk associated with multi-modal large reasoning models (MLRMs), showing that adversaries can infer…

Global: AI Agents Show Normative Equivalence in Public Goods GameA recent online experiment involving 236 participants examined how artificial intelligence agents influence cooperative behavior in small groups. Conducted using a…

Global: Safety Chain-of-Thought Boosts Large Language Model Defenses Against Jailbreak AttacksA novel defense framework called Safety Chain-of-Thought (SCoT) has been introduced to mitigate jailbreak attempts on large language models (LLMs),…

Global: Study Finds LLM-Simulated Users May Misrepresent Agent Performance Across Demographics A recent arXiv paper reports that researchers conducted a cross‑national user study involving participants from the United States, India,…

Global: New Holistic XAI Framework Aims to Boost Transparency in Financial AIA research team has introduced Holistic eXplainable AI (H‑XAI), a framework designed to improve transparency and fairness in artificial‑intelligence…

Global: Study Examines Payoff and Language Effects on LLM Agent CooperationA paper posted to arXiv on Jan. 27, 2026 by a team of sixteen researchers—including Trung‑Kiet Huynh, Dao‑Sy Duy‑Minh, and…

Global: Evaluation of LLM Detector Robustness Reveals Domain SensitivityOn 9 January 2026, researchers Jivnesh Sandhan, Harshit Jaiswal, Fei Cheng, and Yugo Murawaki submitted a paper to arXiv titled “Can We Trust LLM Detectors?” The…

Global: Researchers Propose Reinforcement‑Learning Adversarial Augmentation to Strengthen LLM Function CallsOverview of the New ApproachResearchers have introduced an adversarial data‑augmentation technique that employs reinforcement learning to improve the function‑call capabilities…