Crossing

Follow this topic Ask about this topic

Momentum

5 papers in the last four weeks, against 1 the four weeks before. 0.1% of all new papers.

Jul 6Week of Sep 21

Latest papers 22

All topics

Cultural Divergence Preservation: Diagnosing Flattening and Caricature in LLM-Simulated Survey Populations
Sep 24, 2026Yeeun Chae, Yewon Choi, Seunghyun Lee +1Large Language Model Evaluation Survey
Yonsei University · NAVER · Seoul National University Hospital
Cross-Country Code-Mixing for Generative Recommendation
Sep 24, 2026Yuan Gao, Hao Deng, Haibo Xing +5Cross-Encoder Crossing
Alibaba International Digital Commerce Group Beijing, China · Alibaba International Digital Commerce Group Hangzhou, China
Harm Laundering in GPT Models: Evidence That Gender Discrimination Is Transformed Rather Than Reduced Across Safety-Trained Generations
Sep 17, 2026Sarah Wyer, Sue Black, Noura Al MoubayedToxicity Large Language Model Safety
Durham University
Feeling Terrain Before Crossing: World Models for Off-Road Navigation
Sep 17, 2026E-In Son, Dong-Wook Kim, Ji-Hoon Hwang +4Proprioception World Models
Department of Electrical & Computer Engineering, Seoul National University, Republic of Korea
Bias-Induced Crossover in Absolute Capacity of Dense Associative Memory
Sep 15, 2026Yuto Sakurai, Takeaki Shimokawa, Kazunori Iwata +1Dense Associative Memory Hopfield Networks
Graduate School of Information Sciences, Hiroshima City University, 3-4-1 Ohtsuka-higashi, Asaminami-ku, Hiroshima 731-3194, Japan · RIKEN Center for Advanced Intelligence Project and The University of Tokyo
CROSS: Cascaded Distillation and Dual-Constraint Grounding for Remote Sensing Referring Segmentation
Aug 4, 2026Tingzhang Luo, Ruizhong Liu, Yichao Liu +3Remote Sensing Image Segmentation Spatial Supervision
City University of Hong Kong · The Hong Kong University of Science and Technology (Guangzhou) · Nankai University +1
UniCross: Unified Cross-Skill Dexterous Manipulation Synthesis
Jul 30, 2026Hui Zhang, Julian Ferchow, Jie Song +1Dexterous Manipulation Long-Horizon Manipulation
ETH Zürich, Switzerland · inspire AG, Zürich, Switzerland · HKUST (Guangzhou), China
Crossing the Margin Cliff: Toward Relearn-Robust LLM Unlearning via Margin Calibration
Jul 30, 2026Xiangyu Yin, Jiaxu Liu, Zhen Chen +1Large Language Model Unlearning Loss Function
Chalmers University of Technology, Gothenburg, Sweden · Imperial College London, London, United Kingdom · University of Liverpool, Liverpool, United Kingdom +1
Crossing-Free Probabilistic K-Line Forecasts Without Retraining
Jul 29, 2026Runyao Yu, Yuchen Tao, Yujie Chen +2Probabilistic Forecasting Forecast
London Business School London, United Kingdom · RWTH Aachen University Aachen, Germany · The Chinese University of Hong Kong Shenzhen, China +1
Ground Truth First: A Longitudinal Evaluation Instrument for Agent Memory, and the Tenure Crossover in Memory-Architecture Rankings
Jul 24, 2026Quentin SpencerConversational Memory Interaction History
Independent Researcher
Audio Cross Verification Using Dual Alignment Likelihood Ratio Test
Jul 20, 2026Heidi Lei, Arm Wonghirundacha, Irmak Bukey +1Tamper Localization Audio Understanding
†Massachusetts Institute of Technology · ‡Pomona College · §Harvey Mudd College
Separating Representation from Reconstruction Enables Scalable Text Encoders
Jul 4, 2026Megi Dervishi, Mathurin Videau, Yann LeCunSentence Encoders Encoders
FAIR · 3New York University
Multi-modal Rail Crossing Safety Analysis
Jul 1, 2026Paimon Goulart, Chansong Lim, Nícolas Roque dos Santos +4Relighting Crossing
University of California, Riverside Riverside, California, USA · Riverside County Transportation Commission Riverside, California, USA
Efficient Cross-Scale Invertible Hiding Network with Spatial-Frequency Collaboration and Non-Invertible Mechanism
Jun 24, 2026Junxue Yang, Xin LiaoTwo-Level Spatial-Frequency Fusion Strategy Equivariant Neural Networks
College of Computer Science and Electronic Engineering, Hunan University, Changsha, China
Crossing the Validation Crisis: Cross-Validation Reduces Benchmarking Variance Surprisingly Well
Jun 10, 2026Célestin Eve, Gaël Varoquaux, Thomas MoreauCross Validation Variance
MIND Team, Université Paris-Saclay, Inria, CEA, Palaiseau, France · SODA Team, Inria, Palaiseau, France · Probabl
AI Sovereignty as National Learning Capacity: A Human-Centered Learning Mechanics Viewpoint on France, the United States, and China
May 30, 2026Kim Phuc TranArtificial Intelligence Governance Eu Artificial Intelligence Act
Univ. Lille, ENSAIT, ULR 2461 - GEMTEX - G´enie et Mat´eriaux Textiles, F-59000 Lille, France
Look Both Ways Before You Cross: Lifting Cross Fields From 2D Visual Priors
May 25, 2026Dale Decatur, Jacob Serfaty, Oded Stein +2Meshes Visual Priors
University of Chicago, USA · University of Southern California, USA · Technion, Israel +1
Global Automation Atlas
May 16, 2026Prashant Garg, Tommaso Crosta, Jasmin BaierAutomated Crossing
Imperial College London · Bocconi University · University of Oxford
On the Impact of Crossover in Many-Objective Optimization: A Runtime Analysis of NSGA-III
May 11, 2026Andre OprisMulti-Objective Optimization Crossing
Chair of Algorithms for Intelligent Systems, University of Passau, Passau, Germany
CrossPan: A Comprehensive Benchmark for Cross-Sequence Pancreas MRI Segmentation and Generalization
Apr 20, 2026Linkai Peng, Cuiling Sun, Zheyuan Zhang +10Multimodal Domain Generalization Crossing
Department of Radiology, Northwestern University, Chicago, USA. · Department of Electrical and Computer Engineering, Northwestern University, Evanston, USA. · Department of Computer Science, Northwestern University, Evanston, USA. +4
Polarization and Integration in Global AI Research
Apr 19, 2026Luca Gallo, Riccardo Di Clemente, Balázs LengyelArtificial Intelligence Research Scientific Discovery
ANETI Lab, Corvinus Institute for Advanced Studies, Corvinus University of Budapest, Közrakt´ar u. 4-6, Budapest, 1093, Hungary. · Center for Social Data Science (SODAS), University of Copenhagen, Øster Farimagsgade 5A, Copenhagen, 1353, Denmark. · Complex Connections Lab, Network Science Institute, Northeastern University London, London, E1W 1LP, United Kingdom. +3
Do Vision-Language Models Truly Perform Vision Reasoning? A Rigorous Study of the Modality Gap
Apr 17, 2026Yige Xu, Yongjie Wang, Zizhuo Wu +3Recent Vision-Language Models Multimodal Reasoning
College of Computing and Data Science, Nanyang Technological University, Singapore · Alibaba-NTU Global e-Sustainability CorpLab (ANGEL) · Tongyi Lab, Alibaba Group, China

Sep 24, 2026, cs.CLJ/K move · Enter open · S save

Cultural Divergence Preservation: Diagnosing Flattening and Caricature in LLM-Simulated Survey Populations

Yeeun Chae, Yewon Choi, Seunghyun Lee, IL Im

Yonsei University · NAVER · Seoul National University Hospital

Large Language Model Evaluation Survey Divergence Personality Distributional Fidelity Crossing

Open paper AskPDF arXiv

Large language models (LLMs) are increasingly used as synthetic survey respondents to estimate population response distributions. In cross-cultural survey simulation, evaluations should assess not only distributional fidelity within countries but also whether differences across countries are preserved. However, existing distance-based metrics such as Jensen--Shannon divergence (JSD) do not directly capture such cross-country differences. To address this limitation, we introduce Cultural Divergence Preservation (CDP), a reference-light diagnostic based on a one-time human calibration. CDP identifies reduced cross-country divergence as cultural flattening and increased divergence as cultural caricature. To evaluate CDP, we conduct experiments across four LLM backbones, three persona-based prompting methods, and two survey domains, the World Values Survey (WVS) and the Big Five Personality Test. The results reveal a systematic discrepancy between conventional fidelity metrics and CDP. Controlled experiments show that CDP changes monotonically as cross-country divergence is attenuated or amplified, while the corresponding changes in JSD remain relatively small. In our audit of real LLM generations, DeepPersona-Inspired prompting is frequently favored by conventional fidelity metrics but exhibits the strongest flattening in every model--domain block. CDP thus complements fidelity metrics by directly quantifying the attenuation or amplification of cross-country divergence.

Momentum

Related topics

Latest papers 22