Imagen de Portada

How Do Decoder-Only LLMs Perceive Users? Rethinking Attention Masking for User Representation Learning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Yuan, Jiahao, Xu, Yike, Wen, Jinyong, Wang, Baokun, Chen, Yang, Lin, Xiaotong, Huang, Wuliang, Gao, Ziyi, Fu, Xing, Cheng, Yu, Wang, Weiqiang
Formato:	Preprint
Publicado:	2026
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Instruction-aware User Embedding via Synergistic Language and Representation Modeling
por: Gao, Ziyi, et al.
Publicado: (2025)

Query as Anchor: Scenario-Adaptive User Representation via Large Language Model
por: Yuan, Jiahao, et al.
Publicado: (2026)

Learning Unified User Quantized Tokenizers for User Representation
por: He, Chuan, et al.
Publicado: (2025)

Transferable and Forecastable User Targeting Foundation Model
por: Dou, Bin, et al.
Publicado: (2024)

The Siren Song of LLMs: How Users Perceive and Respond to Dark Patterns in Large Language Models
por: Shi, Yike, et al.
Publicado: (2025)

Gated Tree Cross-Attention for Checkpoint-Compatible Syntax Injection in Decoder-Only LLMs
por: Gao, Xinyu, et al.
Publicado: (2026)

Decoder-Only LLMs are Better Controllers for Diffusion Models
por: Dong, Ziyi, et al.
Publicado: (2025)

Safe for Whom? Rethinking How We Evaluate the Safety of LLMs for Real Users
por: Kempermann, Manon, et al.
Publicado: (2025)

Bitune: Leveraging Bidirectional Attention to Improve Decoder-Only LLMs
por: Kopiczko, Dawid J., et al.
Publicado: (2024)

UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation
por: Zhang, Tao, et al.
Publicado: (2025)

When, What, and How: Rethinking Retrieval-Enhanced Speculative Decoding
por: Fang, Min, et al.
Publicado: (2025)

Rethinking Theory of Mind Benchmarks for LLMs: Towards A User-Centered Perspective
por: Wang, Qiaosi, et al.
Publicado: (2025)

Attention-Constrained Inference for Robust Decoder-Only Text-to-Speech
por: Wang, Hankun, et al.
Publicado: (2024)

RealFin: How Well Do LLMs Reason About Finance When Users Leave Things Unsaid?
por: Dai, Yuyang, et al.
Publicado: (2026)

Toward Machine Translation Literacy: How Lay Users Perceive and Rely on Imperfect Translations
por: Xiao, Yimin, et al.
Publicado: (2025)

Rethinking Tokenizer and Decoder in Masked Graph Modeling for Molecules
por: Liu, Zhiyuan, et al.
Publicado: (2023)

Screencast-Based Analysis of User-Perceived GUI Responsiveness
por: Liu, Wei, et al.
Publicado: (2025)

Be Friendly, Not Friends: How LLM Sycophancy Shapes User Trust
por: Sun, Yuan, et al.
Publicado: (2025)

FreeMask: Rethinking the Importance of Attention Masks for Zero-Shot Video Editing
por: Cai, Lingling, et al.
Publicado: (2024)

SemanticMIM: Marring Masked Image Modeling with Semantics Compression for General Visual Representation
por: Yuan, Yike, et al.
Publicado: (2024)

CURP: Codebook-based Continuous User Representation for Personalized Generation with LLMs
por: Wang, Liang, et al.
Publicado: (2026)

Mobile Open‐Source Software Reliability Growth Model Based on Extended Weibull Distribution and Introduced Faults With Multiple Change‐Points
por: Jinyong Wang, et al.
Publicado: (2026)

Rethinking the Evaluation of Dialogue Systems: Effects of User Feedback on Crowdworkers and LLMs
por: Siro, Clemencia, et al.
Publicado: (2024)

Can We Predict the Next Question? A Collaborative Filtering Approach to Modeling User Behavior
por: Fu, Bokang, et al.
Publicado: (2025)

Do LLMs Implicitly Determine the Suitable Text Difficulty for Users?
por: Gobara, Seiji, et al.
Publicado: (2024)

How Users Perceive Mixed-Initiative AI: Attitudes Toward Assistance in Problem Solving
por: Luo, Yunhao, et al.
Publicado: (2026)

Scaling User Modeling: Large-scale Online User Representations for Ads Personalization in Meta
por: Zhang, Wei, et al.
Publicado: (2023)

A Comprehensive Study of Decoder-Only LLMs for Text-to-Image Generation
por: Wang, Andrew Z., et al.
Publicado: (2025)

Enhanced Structured State Space Models via Grouped FIR Filtering and Attention Sink Mechanisms
por: Meng, Tian, et al.
Publicado: (2024)

Modeling Stage-wise Evolution of User Interests for News Recommendation
por: Cheng, Zhiyong, et al.
Publicado: (2026)

DOA: Training-Free Decoder-Only Attention Policy for Long-Form Simultaneous Translation with SpeechLLMs
por: Papi, Sara, et al.
Publicado: (2026)

Rethinking Patch Dependence for Masked Autoencoders
por: Fu, Letian, et al.
Publicado: (2024)

Trained Persistent Memory for Frozen Decoder-Only LLMs
por: Jeong, Hong
Publicado: (2026)

Scaling Sparse and Dense Retrieval in Decoder-Only LLMs
por: Zeng, Hansi, et al.
Publicado: (2025)

Do LLMs Benefit from User and Item Embeddings in Recommendation Tasks?
por: Hossain, Mir Rayat Imtiaz, et al.
Publicado: (2026)

MobileUPReg: Identifying User-Perceived Performance Regressions in Mobile OS Versions
por: Liu, Wei, et al.
Publicado: (2025)

Intersectional Sycophancy: How Perceived User Demographics Shape False Validation in Large Language Models
por: Maltbie, Benjamin, et al.
Publicado: (2026)

Predictive Target-to-User Association in Complex Scenarios via Hybrid-Field ISAC Signaling
por: Yuan, Yifeng, et al.
Publicado: (2025)

Engagement, User Satisfaction, and the Amplification of Divisive Content on Social Media
por: Milli, Smitha, et al.
Publicado: (2023)

Robot Imports and Firms' Export Adjustment: Evidence From Chinese Exporters
por: Jinyong Zhan, et al.
Publicado: (2025)