Profile

Follow this topic Ask about this topic

Momentum

4 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 40

All topics

From "Who Is This User?" to "What Does This Purchase Mean?": A Deployed Pipeline for Semantic User Profiling at Bank Scale
Sep 17, 2026Ryota Mitsuhashi, Tetsuro Morimura, Hirotake ItoProfile Large Language Model Pipelines
CyberAgent, Tokyo, Japan
Reproducing Transparent and Scrutable Recommendations: Exploring Open-Weight Models via Natural-Language User Profiles
Sep 17, 2026Noah Mamié, Laurin van den BerghProfile Transparency
University of Zurich Department of Informatics
SA-Profile: Automated Sulcus Angle Profiling from Super-Resolution MRI
Sep 9, 2026Michael Wehrli, Leo Widmer, Edwin Li +5Morphometric Analysis Feet
Department of Biomedical Engineering, University Basel, Switzerland · Department of Orthopedics, University Children’s Hospital Basel, Switzerland
Less Is Personal: Learning Minimal Sufficient User Profiles for Personalized Language Models
Sep 8, 2026Minghang Liu, Qiang Qiu, Yuanzhuo Wang +2Large Language Model Personalization Personalization
State Key Laboratory of AI Safety, Institute of Computing Technology, CAS · University of Chinese Academy of Sciences, Beijing, China
VIBE-Bench: Evaluating Personalized Large Language Models When Profiles Don't Mean Preferences
Sep 1, 2026Yiwen Jiang, Yang Deng, Stephanie Fong +9Large Language Model Personalization Preference Alignment Learning
1Monash University · 2Singapore Management University · University of Liverpool +1
A Dual-Cam Parallel Elastic Actuator with Shared Gas-Spring Compensation for Humanoid Ankles
Aug 31, 2026Jingcheng Jiang, Yifang Zhang, Nikos G. TsagarakisSoft Pneumatic Actuators Torque
Humanoids and Human Centered Mechatronics (HHCM) Research Line Istituto Italiano di Tecnologia Genova, Italy
Recovering Lesion Parameters from Aphasic Picture Naming Error Profiles in Large Language Models
Aug 5, 2026Yong Yang, Roger Newman-Norlund, Xiang Guan +10Large Language Models Fail Dysarthric Speech
Department of Computer Science and Engineering, University of South Carolina · Department of Communication Sciences and Disorders, University of South Carolina · ALLT.AI, LLC +3
The Personalization Mirage: How LLMs Fabricate User Profiles, and Why Self-Monitoring Misleads
Aug 5, 2026Yushi Sun, Yanjie Zhang, Rui ShengProfile Personalization
LIGHTSPEED, Shenzhen, China · The Hong Kong University of Science and Technology, Hong Kong, China · Tencent LIGHTSPEED
AIGen: Automating AI Bill of Materials Generation Through Hybrid MLOps Integration
Jul 29, 2026Federica Pepe, Daniele Bifolco, Costantino Martignetti +4Artificial Intelligence Risk Profile
University of Sannio Benevento, Italy · Smart Shaped s.r.l. Pescara, Italy
Aligning LLM-Simulated and Human Examinees for Psychometric Calibration: A Cognitive Diagnostic Profiling Approach
Jul 28, 2026Wenjie Zhou, Yunting Liu, Renjiao Tang +1Psychometric Properties Cognitive Diagnosis
Berkeley School of Education, University of California, Berkeley · Department of Family Social Science, University of Minnesota Twin Cities, Minneapolis
TRWH: A Text-Driven Random Walk Heterogeneous GNN for Semantic-Aware Sparse Recommendation
Jul 28, 2026He Ma, Chen LiuReal-World Content Recommendation Problem Graph Neural Networks
The University of Sydney Camperdown, NSW, 2006, Australia · Nankai University Tianjing, China
Toward Personalized Social Robots for Child Well-being: Data Requirement Principles from a Recommender-System Perspective
Jul 6, 2026Jin Huang, Eric Nichols, Fethiye Irmak Dogan +1Children Profile
University of Cambridge, Cambridge, United Kingdom · Honda Research Institute Japan, Wako, Japan
PromptPET: Privacy-Utility Optimized Prompt Obfuscation
Jul 3, 2026Ke Yang, Olivia Figueira, Umar Iqbal +1Privacy-Utility Trade-Offs Obfuscation
University of California, Irvine Irvine, CA, USA · Washington University in St. Louis St. Louis, MO, USA
SocialPersona: Benchmarking Personalized Profiling and Response with Multimodal Social-Media Context
Jun 25, 2026Qinkai Zhang, Yanyan Zhao, Xin Lu +3Persona Consistency Social Media Timeline Dynamics
Harbin Institute of Technology
ProfileFoundry: A Synthetic Person-Object Substrate for Privacy, Memory, and Tool-Use Evaluation in LLM Agent
Jun 24, 2026Sriram Selvam, Anneswa GhoshProfile Synthetic Data
ProfiLLM: Utility-Aligned Agentic User Profiling for Industrial Ride-Hailing Dispatch
Jun 17, 2026Tengfei Lyu, Zirui Yuan, Xu Liu +4Profile Profiling
HKUST(GZ) · Didichuxing Co. Ltd
EComAgentBench: Benchmarking Shopping Agents on Long-Horizon Tasks with Distributed Hidden Intent
Jun 16, 2026Zeyao Du, Tong Li, Haibo ZhangAgentic Commerce Agentic Benchmarks
Shopee
PAL-Bench: Evidence-Grounded Profile Reconstruction from Longitudinal Personal Albums
Jun 15, 2026Qiwei Yan, Zhiqiang Yuan, Zexi Jia +4Profile Re-Identification
University of Chinese Academy of Sciences, Beijing, China · 1WeChat AI, Tencent, Beijing, China · 3Beihang University, Beijing, China +1
Trait, Not State: The Durability of Reading Identity in Social Highlighting
Jun 11, 2026Kazuki Nakayashiki, Keisuke WatanabeProfile
Glasp Inc.
Debiasing Without Protected Attributes: Latent Concept Erasure from Textual Profiles
Jun 10, 2026Shun Shao, Zheng Zhao, Anna Korhonen +2Debiasing Large Language Model Bias
University of Cambridge · University of Edinburgh · University of Groningen +1
Self-supervised User Profile Generation for Personalization
Jun 3, 2026Clark Mingxuan Ju, Yuwei Qiu, Tong Zhao +1Large Language Model Personalization Profile
Snap Inc. · Bellevue, WA USA
NBQ: Next-Best-Question for Dynamic Profiling
May 30, 2026Yimin Shi, Clarice Wang, Haixun Wang +1Profile Distribution Matching
National University of Singapore Singapore, Singapore · University of Pennsylvania Philadelphia, PA, USA · EvenUp San Francisco, CA, USA
Who Am I? History-Aware Profiles for Student Simulation in Tutoring Dialogues
May 28, 2026Zhangqi Duan, Shuyan Huang, Alexander Scarlatos +3User Simulation Tutors
University of Massachusetts Amherst · 2Eedi
ChildEval: When large language models meet children's personalities
May 27, 2026Yanyan Luo, Xue Han, Chunxu Zhao +5Large Language Model Evaluation Personality
JIUTIAN Research, China Mobile, Beijing, China
Diagnosing Live Within-Policy Instruction Conflicts in LLM Agents with Witnessed Resolution Profiles
May 27, 2026Lu Yan, Xuan Chen, Xiangyu ZhangLarge Language Model Policy Optimization Large Language Model Agents
Purdue University
StreamProfileBench: A Benchmark for Fine-Grained User Profile Inference in Real-World Streaming Scenarios
May 25, 2026Sizhe Wang, Feiyu Duan, Juelin Wang +2Profile Large Language Model Personalization
School of Data Science, Fudan University · Shanghai University of Finance and Economics · Shanghai Innovation Institute +2
Exploring Profiles of Cognitive Distortions Associated with Mental Health Disorders
May 24, 2026Alina Anikejeva, Kairit SirtsMental Health Cognitive Science
Institute of Computer Science · University of Tartu · Tartu, Estonia
UserGPT Technical Report
May 9, 2026Yunyi Xuan, Hao Yi, Fengling Mao +9User Modeling Artificial Intelligence Personas
1Alibaba Group
Bridging Textual Profiles and Latent User Embeddings for Personalization
May 7, 2026Zhaoxuan Tan, Xiang Zhai, Yan Zhu +2Multimodal Recommendation Model Large Language Model Personalization
University of Notre Dame · 2Google · * This work was done while Zhaoxuan was a student researcher at Google.
The AI Legal Specialist: A Juridically Autonomous Professional Profile for AI Governance
May 7, 2026Nicola FabianoEu Artificial Intelligence Act Artificial Intelligence Governance
Studio Legale Fabiano, Italy
Towards Self-Referential Analytic Assessment: A Profile-Based Approach to L2 Writing Evaluation with LLMs
May 5, 2026Stefano Bannò, Kate Knill, Mark GalesAutomated Essay Scoring Self-Evaluation
ALTA Institute, Department of Engineering, University of Cambridge (UK)
When Agents Shop for You: Role Coherence in AI-Mediated Markets
Apr 29, 2026Soogand Alavi, Salar NozariAgentic Commerce Preference Alignment Learning
Tippie College of Business, University of Iowa
PrismaDV: Automated Task-Aware Data Unit Test Generation
Apr 23, 2026Hao Chen, Arnab Phani, Sebastian SchelterTest Generation Data Science Agents
BIFOLD & TU Berlin
Pre-trained LLMs Meet Sequential Recommenders: Efficient User-Centric Knowledge Distillation
Apr 23, 2026Nikita Severin, Danil Kartushov, Vladislav Urzhumov +8Multimodal Recommendation Model Real-World Content Recommendation Problem
Independent researcher, Belgrade, Serbia · ITMO University, Saint Petersburg, Russia · Innopolis University, Innopolis, Russia +3
Dialect vs Demographics: Quantifying LLM Bias from Implicit Linguistic Signals vs. Explicit User Profiles
Apr 22, 2026Irti Haq, Belén SaldíasLarge Language Model Bias Large Language Model Safety
University of Washington, USA
Before You Interpret the Profile: Validity Scaling for LLM Metacognitive Self-Report
Apr 20, 2026Jon-Paul CacioliPsychometric Properties Self-Evaluation
Independent Researcher, Melbourne, Australia
Decomposing the Depth Profile of Fine-Tuning
Apr 19, 2026Jayadev BillaLayer-Wise Model Fine-Tuning
VeriX-Anon: A Multi-Layered Framework for Mathematically Verifiable Outsourced Target-Driven Data Anonymization
Apr 14, 2026Miit Daga, Swarna Priya RamuAnonymization Dataset Ownership Verification
School of Computer Science Engineering and Information Systems, Vellore Institute of Technology, Vellore, 632014, Tamil Nadu, India
PeopleSearchBench: Evaluating AI-Powered People Search Platforms with Criteria-Grounded Verification
Mar 29, 2026Tianyu Shi, Wei Wang, Zequn Xie +10Jobs Profile
ProPS: Prompted Profile Synthesis for Natural Language-Conditioned Speaker Embedding Distributions
Date pendingThomas Thebaud, Junhyeok Lee, Laureano Moro-Velazquez +2Speech Synthesis Speaker
Department of Electrical and Computer Engineering, Johns Hopkins University, Baltimore, MD, USA · AMIAD, Palaiseau, France · Department of Signal Theory and Communications, Universidad Carlos III de Madrid (UC3M), Leganes, Spain

Sep 17, 2026, cs.AIJ/K move · Enter open · S save

From "Who Is This User?" to "What Does This Purchase Mean?": A Deployed Pipeline for Semantic User Profiling at Bank Scale

Ryota Mitsuhashi, Tetsuro Morimura, Hirotake Ito

CyberAgent, Tokyo, Japan

Profile Large Language Model Pipelines Natural Language Inference Transaction Evidence LLM Inference Optimization Prevalence

Open paper AskPDF arXiv

Per-user LLM inference on transaction histories binds the inference budget linearly to user count, which becomes prohibitive at applied scale. We re-cast attribute inference from per-user to per-transaction-pattern. The pipeline runs in three phases: Resolve abstracts item names with optional web grounding, Profile infers attributes for each frequent pattern, and Tag clusters free-text attributes into a queryable database. In Profile, a single LLM call per pattern emits predefined categorical labels, free-text attributes, and per-attribute prevalence estimates. Because inference runs over patterns rather than users, the budget grows with the pattern count rather than the user count. On the public Open e-commerce corpus, the database is statistically indistinguishable from an LLM that reads each user's raw history directly in AUC across the evaluated attributes, and the prevalence estimates carry discriminative signal between positive and negative users. The pipeline is deployed at a major Japanese bank profiling on the order of tens of millions of users, with close to a three-order-of-magnitude reduction in LLM inference targets versus a per-user pipeline. The code is publicly available on https://github.com/CyberAgentAILab/profiling-agent-open-ecommerce.

Momentum

Related topics

Latest papers 40