·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Regret-Optimal Wasserstein-Robust Linear Regression1h◆Accelerating Min-Max Optimization via Power-Law Stepsizes1h◆Fair Recommender Systems for Intersecting Groups1h◆RC Prediction: A Python Package for Parameter-Aware Reservoir Computing1h◆SPT-Flow: One Integration, Many Futures in Continuous-Time World Models1h◆GhostPrefix: Synchronization-Free Universal Prefix Attacks for ASR Manipulation1h◆New Lower Bounds for Private PAC Learning1h◆When Does Jacobian Fine-Tuning Stabilize Neural PDE Emulators?1h◆SAT-ACT: Learning CDCL Branching from Outcome-Derived Action Preferences1h◆Conveyance: A Versatile Framework for Learning in Structured Class Spaces1h◆Co-optimization for Adaptive Conformal Prediction1h◆CEFR Level Assessment across Languages and Text Granularities1h◆RangeSWA: Training-Free Length Extrapolation for Continuous Diffusion Language Models1h◆TurnTurk-GPT: Text-Based Turn-Taking Prediction for Turkish1h◆Asynchronous Flow Map Language Models1h◆CRoS: Causality Reward on Scrambled CoTs Improves Accuracy and Reasoning Faithfulness1h◆PersonaChatBench: Evaluating Chat Assistants with Diverse Simulated Users1h◆Subquadratic Attention with a Hierarchical Tree-Structured Indexer1h◆DecisionRank: On-Policy Distillation for Decision-Model Rerankers1h◆Flide: Accelerating Decision Inference with Exact State Forking1h◆Regret-Optimal Wasserstein-Robust Linear Regression1h◆Accelerating Min-Max Optimization via Power-Law Stepsizes1h◆Fair Recommender Systems for Intersecting Groups1h◆RC Prediction: A Python Package for Parameter-Aware Reservoir Computing1h◆SPT-Flow: One Integration, Many Futures in Continuous-Time World Models1h◆GhostPrefix: Synchronization-Free Universal Prefix Attacks for ASR Manipulation1h◆New Lower Bounds for Private PAC Learning1h◆When Does Jacobian Fine-Tuning Stabilize Neural PDE Emulators?1h◆SAT-ACT: Learning CDCL Branching from Outcome-Derived Action Preferences1h◆Conveyance: A Versatile Framework for Learning in Structured Class Spaces1h◆Co-optimization for Adaptive Conformal Prediction1h◆CEFR Level Assessment across Languages and Text Granularities1h◆RangeSWA: Training-Free Length Extrapolation for Continuous Diffusion Language Models1h◆TurnTurk-GPT: Text-Based Turn-Taking Prediction for Turkish1h◆Asynchronous Flow Map Language Models1h◆CRoS: Causality Reward on Scrambled CoTs Improves Accuracy and Reasoning Faithfulness1h◆PersonaChatBench: Evaluating Chat Assistants with Diverse Simulated Users1h◆Subquadratic Attention with a Hierarchical Tree-Structured Indexer1h◆DecisionRank: On-Policy Distillation for Decision-Model Rerankers1h◆Flide: Accelerating Decision Inference with Exact State Forking1h◆
News/Can Humans Tell? A Dual-Axis Study of Human Perception of LLM-Generated News
arxiv
PublishedNovember 2, 2026 at 5:00 AM

Can Humans Tell? A Dual-Axis Study of Human Perception of LLM-Generated News

Source
arxiv.orgfull article ↗
Read on arxiv→
Publisher summary· verbatim

arXiv:2604.03755v2 Announce Type: replace-cross Abstract: Can humans tell whether a news article was written by a person or a large language model (LLM)? We investigate this question using JudgeGPT, a study platform that independently measures source attribution (human vs. machine) and authenticity

Stay posted· Newsletter

Three short emails a week: Monday, Wednesday and Friday. Top movers, new models and the most-referenced story.

// no spam · unsubscribe one-click · free forever

Your email is used only to send The Bubble Brief. Privacy policy

Discussion
Source
↗
arxiv
Read original ↗All from arxiv →

No replies yet. Be first.

Source
↗
arxiv
Read original ↗All from arxiv →

Related coverage

More from ARXIV
arxivRegret-Optimal Wasserstein-Robust Linear Regression1harxivAccelerating Min-Max Optimization via Power-Law Stepsizes1harxivFair Recommender Systems for Intersecting Groups1harxivRC Prediction: A Python Package for Parameter-Aware Reservoir Computing1h
The Bubble Brief
MON · WED · FRI

Read AI insights every Monday, Wednesday and Friday — top movers, new models, story of the week.

// no spam · unsubscribe one-click · free forever

Your email is used only to send The Bubble Brief. Privacy policy

Originally published on arxiv ↗
PrivacyTermsRefundsLegal notice|AboutMethodologyContact

© 2026 Databubble

Built by Marouane Gazouzi · Readyo, AI interview coach

HomeModelsNews