Cover Image

Persona Vectors: Monitoring and Controlling Character Traits in Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chen, Runjin, Arditi, Andy, Sleight, Henry, Evans, Owain, Lindsey, Jack
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

All Code, No Thought: Current Language Models Struggle to Reason in Ciphered Language
by: Guo, Shiyuan, et al.
Published: (2025)

Weird Generalization and Inductive Backdoors: New Ways to Corrupt LLMs
by: Betley, Jan, et al.
Published: (2025)

Where Do Reasoning Models Refuse?
by: Yamaguchi, Kureha, et al.
Published: (2025)

The Consciousness Cluster: Emergent preferences of Models that Claim to be Conscious
by: Chua, James, et al.
Published: (2026)

Thought Crime: Backdoors and Emergent Misalignment in Reasoning Models
by: Chua, James, et al.
Published: (2025)

Refusal in Language Models Is Mediated by a Single Direction
by: Arditi, Andy, et al.
Published: (2024)

Language Models Implement Simple Word2Vec-style Vector Arithmetic
by: Merullo, Jack, et al.
Published: (2023)

Found in the Middle: How Language Models Use Long Contexts Better via Plug-and-Play Positional Encoding
by: Zhang, Zhenyu, et al.
Published: (2024)

Mixture-of-Personas Language Models for Population Simulation
by: Bui, Ngoc, et al.
Published: (2025)

Slot Machines: How LLMs Keep Track of Multiple Entities
by: Bogdan, Paul C., et al.
Published: (2026)

Persona-aware Generative Model for Code-mixed Language
by: Sengupta, Ayan, et al.
Published: (2023)

CEV-LM: Controlled Edit Vector Language Model for Shaping Natural Language Generations
by: Moorjani, Samraj, et al.
Published: (2024)

Real-Time Detection of Hallucinated Entities in Long-Form Generation
by: Obeso, Oscar, et al.
Published: (2025)

Abstractive Red-Teaming of Language Model Character
by: Rahn, Nate, et al.
Published: (2026)

Jailbreaking Large Language Models Against Moderation Guardrails via Cipher Characters
by: Jin, Haibo, et al.
Published: (2024)

Open Character Training: Shaping the Persona of AI Assistants through Constitutional AI
by: Maiya, Sharan, et al.
Published: (2025)

Behavioral Steering in a 35B MoE Language Model via SAE-Decoded Probe Vectors: One Agency Axis, Not Five Traits
by: Yap, Jia Qing
Published: (2026)

Stress-Testing Model Specs Reveals Character Differences among Language Models
by: Zhang, Jifan, et al.
Published: (2025)

CharED: Character-wise Ensemble Decoding for Large Language Models
by: Gu, Kevin, et al.
Published: (2024)

Function Vectors in Large Language Models
by: Todd, Eric, et al.
Published: (2023)

PersonaGym: Evaluating Persona Agents and LLMs
by: Samuel, Vinay, et al.
Published: (2024)

White-Box Sensitivity Auditing with Steering Vectors
by: Cyberey, Hannah, et al.
Published: (2026)

Personas as a Way to Model Truthfulness in Language Models
by: Joshi, Nitish, et al.
Published: (2023)

Adaptive Task Vectors for Large Language Models
by: Kang, Joonseong, et al.
Published: (2025)

The LLM Has Left The Chat: Evidence of Bail Preferences in Large Language Models
by: Ensign, Danielle, et al.
Published: (2025)

Transferring Linear Features Across Language Models With Model Stitching
by: Chen, Alan, et al.
Published: (2025)

Negation Neglect: When models fail to learn negations in training
by: Mayne, Harry, et al.
Published: (2026)

Revisiting Character-level Adversarial Attacks for Language Models
by: Rocamora, Elias Abad, et al.
Published: (2024)

Can Character-based Language Models Improve Downstream Task Performance in Low-Resource and Noisy Language Scenarios?
by: Riabi, Arij, et al.
Published: (2021)

Training a Bilingual Language Model by Mapping Tokens onto a Shared Character Space
by: Rom, Aviad, et al.
Published: (2024)

The Assistant Axis: Situating and Stabilizing the Default Persona of Language Models
by: Lu, Christina, et al.
Published: (2026)

LoX: Low-Rank Extrapolation Robustifies LLM Safety Against Fine-tuning
by: Perin, Gabriel J., et al.
Published: (2025)

VSPO: Vector-Steered Policy Optimization for Behavioral Control
by: Zhang, Xuechen, et al.
Published: (2026)

Exploring Context Window of Large Language Models via Decomposed Positional Vectors
by: Dong, Zican, et al.
Published: (2024)

Connecting the Dots: LLMs can Infer and Verbalize Latent Structure from Disparate Training Data
by: Treutlein, Johannes, et al.
Published: (2024)

PersonaBOT: Bringing Customer Personas to Life with LLMs and RAG
by: Rizwan, Muhammed, et al.
Published: (2025)

Large Language Models are Superpositions of All Characters: Attaining Arbitrary Role-play via Self-Alignment
by: Lu, Keming, et al.
Published: (2024)

Looking Inward: Language Models Can Learn About Themselves by Introspection
by: Binder, Felix J, et al.
Published: (2024)

RSAVQ: Riemannian Sensitivity-Aware Vector Quantization for Large Language Models
by: Xu, Zukang, et al.
Published: (2025)

The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"
by: Berglund, Lukas, et al.
Published: (2023)