Copertina

Facet-Level Persona Control by Trait-Activated Routing with Contrastive SAE for Role-Playing LLMs

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Tang, Wenqiu, Wan, Zhen, Komamizu, Takahiro, Ide, Ichiro
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Enhancing Persona Consistency for LLMs' Role-Playing using Persona-Aware Contrastive Learning
di: Ji, Ke, et al.
Pubblicazione: (2025)

Tracking Small Birds by Detection Candidate Region Filtering and Detection History-aware Association
di: Liu, Tingwei, et al.
Pubblicazione: (2024)

Action Selection Learning for Multi-label Multi-view Action Recognition
di: Nguyen, Trung Thanh, et al.
Pubblicazione: (2024)

One-Stage Open-Vocabulary Temporal Action Detection Leveraging Temporal Multi-scale and Action Label Features
di: Nguyen, Trung Thanh, et al.
Pubblicazione: (2024)

Q-Adapter: Visual Query Adapter for Extracting Textually-related Features in Video Captioning
di: Chen, Junan, et al.
Pubblicazione: (2025)

Crafting Customisable Characters with LLMs: A Persona-Driven Role-Playing Agent Framework
di: Yang, Bohao, et al.
Pubblicazione: (2024)

Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalization
di: Tseng, Yu-Min, et al.
Pubblicazione: (2024)

Multi-proposal Collaboration and Multi-task Training for Weakly-supervised Video Moment Retrieval
di: Zhang, Bolin, et al.
Pubblicazione: (2026)

OpenCharacter: Training Customizable Role-Playing LLMs with Large-Scale Synthetic Personas
di: Wang, Xiaoyang, et al.
Pubblicazione: (2025)

Memory-Driven Role-Playing: Evaluation and Enhancement of Persona Knowledge Utilization in LLMs
di: Wang, Kai, et al.
Pubblicazione: (2026)

MultiTSF: Transformer-based Sensor Fusion for Human-Centric Multi-view and Multi-modal Action Recognition
di: Nguyen, Trung Thanh, et al.
Pubblicazione: (2025)

View-aware Cross-modal Distillation for Multi-view Action Recognition
di: Nguyen, Trung Thanh, et al.
Pubblicazione: (2025)

MultiSensor-Home: A Wide-area Multi-modal Multi-view Dataset for Action Recognition and Transformer-based Sensor Fusion
di: Nguyen, Trung Thanh, et al.
Pubblicazione: (2025)

Persistent Personas? Role-Playing, Instruction Following, and Safety in Extended Interactions
di: de Araujo, Pedro Henrique Luz, et al.
Pubblicazione: (2025)

PersonaEval: Are LLM Evaluators Human Enough to Judge Role-Play?
di: Zhou, Lingfeng, et al.
Pubblicazione: (2025)

Activation-Space Personality Steering: Hybrid Layer Selection for Stable Trait Control in LLMs
di: Bhandari, Pranav, et al.
Pubblicazione: (2025)

Persona Vectors: Monitoring and Controlling Character Traits in Language Models
di: Chen, Runjin, et al.
Pubblicazione: (2025)

Can LLMs Express Personality Across Cultures? Introducing CulturalPersonas for Evaluating Trait Alignment
di: Dey, Priyanka, et al.
Pubblicazione: (2025)

CharacterGPT: A Persona Reconstruction Framework for Role-Playing Agents
di: Park, Jeiyoon, et al.
Pubblicazione: (2024)

From Persona to Personalization: A Survey on Role-Playing Language Agents
di: Chen, Jiangjie, et al.
Pubblicazione: (2024)

HyCoRA: Hyper-Contrastive Role-Adaptive Learning for Role-Playing
di: Yang, Shihao, et al.
Pubblicazione: (2025)

Moral Susceptibility and Robustness under Persona Role-Play in Large Language Models
di: Costa, Davi Bastos, et al.
Pubblicazione: (2025)

Identifying and Manipulating Personality Traits in LLMs Through Activation Engineering
di: Allbert, Rumi, et al.
Pubblicazione: (2024)

From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
di: Zhang, Rongsheng, et al.
Pubblicazione: (2026)

RMTBench: Benchmarking LLMs Through Multi-Turn User-Centric Role-Playing
di: Xiang, Hao, et al.
Pubblicazione: (2025)

Beyond Profile: From Surface-Level Facts to Deep Persona Simulation in LLMs
di: Wang, Zixiao, et al.
Pubblicazione: (2025)

Personas with Attitudes: Controlling LLMs for Diverse Data Annotation
di: Fröhling, Leon, et al.
Pubblicazione: (2024)

Orca: Enhancing Role-Playing Abilities of Large Language Models by Integrating Personality Traits
di: Huang, Yuxuan
Pubblicazione: (2024)

Self-Prompt Tuning: Enable Autonomous Role-Playing in LLMs
di: Kong, Aobo, et al.
Pubblicazione: (2024)

LLMs + Persona-Plug = Personalized LLMs
di: Liu, Jiongnan, et al.
Pubblicazione: (2024)

Route Before Retrieve: Activating Latent Routing Abilities of LLMs for RAG vs. Long-Context Selection
di: Chen, Yiwen, et al.
Pubblicazione: (2026)

Enhancing Persona Following at Decoding Time via Dynamic Importance Estimation for Role-Playing Agents
di: Liu, Yuxin, et al.
Pubblicazione: (2026)

Small Object Detection for Birds with Swin Transformer
di: Huo, Da, et al.
Pubblicazione: (2025)

PersonaFuse: A Personality Activation-Driven Framework for Enhancing Human-LLM Interactions
di: Tang, Yixuan, et al.
Pubblicazione: (2025)

Facet-Level Tracing of Evidence Uncertainty and Hallucination in RAG
di: Elchafei, Passant, et al.
Pubblicazione: (2026)

Think Like a Person Before Responding: A Multi-Faceted Evaluation of Persona-Guided LLMs for Countering Hate
di: Ngueajio, Mikel K., et al.
Pubblicazione: (2025)

Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering
di: Zhao, Yu, et al.
Pubblicazione: (2024)

DynSess: Dynamic Session-Level Evaluation and Optimization Framework for Role-Playing Agents
di: Zhang, Rongsheng, et al.
Pubblicazione: (2026)

Playing with Voices: Tabletop Role-Playing Game Recordings as a Diarization Challenge
di: Remme, Lian, et al.
Pubblicazione: (2025)

Investigating Conceptual Blending of a Diffusion Model for Improving Nonword-to-Image Generation
di: Matsuhira, Chihaya, et al.
Pubblicazione: (2024)