Imagen de Portada

The Assistant Axis: Situating and Stabilizing the Default Persona of Language Models

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Lu, Christina, Gallagher, Jack, Michala, Jonathan, Fish, Kyle, Lindsey, Jack
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

Emergent Introspective Awareness in Large Language Models
por: Lindsey, Jack
Publicado: (2026)

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

Beyond Static Personas: Situational Personality Steering for Large Language Models
por: Wei, Zesheng, et al.
Publicado: (2026)

Improving Agent Interactions in Virtual Environments with Language Models
por: Zhang, Jack
Publicado: (2024)

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

Emotion Concepts and their Function in a Large Language Model
por: Sofroniew, Nicholas, et al.
Publicado: (2026)

Aligning VLM Assistants with Personalized Situated Cognition
por: Li, Yongqi, et al.
Publicado: (2025)

Generics and Default Reasoning in Large Language Models
por: Kirkpatrick, James Ravi, et al.
Publicado: (2025)

Plant in Cupboard, Orange on Rably, Inat Aphone. Benchmarking Incremental Learning of Situation and Language Model using a Text-Simulated Situated Environment
por: Jordan, Jonathan, et al.
Publicado: (2025)

On Efficient Language and Vision Assistants for Visually-Situated Natural Language Understanding: What Matters in Reading and Reasoning
por: Kim, Geewook, et al.
Publicado: (2024)

ALMs: Authorial Language Models for Authorship Attribution
por: Huang, Weihang, et al.
Publicado: (2024)

A Statistical Physics of Language Model Reasoning
por: Carson, Jack David, et al.
Publicado: (2025)

Leveraging Transformer-Based Models for Predicting Inflection Classes of Words in an Endangered Sami Language
por: Alnajjar, Khalid, et al.
Publicado: (2024)

UNcommonsense Reasoning: Abductive Reasoning about Uncommon Situations
por: Zhao, Wenting, et al.
Publicado: (2023)

S0 Tuning: Zero-Overhead Adaptation of Hybrid Recurrent-Attention Models
por: Young, Jack
Publicado: (2026)

Persona Jailbreaking in Large Language Models
por: Sandhan, Jivnesh, et al.
Publicado: (2026)

Circuit Component Reuse Across Tasks in Transformer Language Models
por: Merullo, Jack, et al.
Publicado: (2023)

Talking Heads: Understanding Inter-layer Communication in Transformer Language Models
por: Merullo, Jack, et al.
Publicado: (2024)

Mechanistic Decomposition of Sentence Representations
por: Tehenan, Matthieu, et al.
Publicado: (2025)

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

When "A Helpful Assistant" Is Not Really Helpful: Personas in System Prompts Do Not Improve Performances of Large Language Models
por: Zheng, Mingqian, et al.
Publicado: (2023)

The Persona Paradox: Medical Personas as Behavioral Priors in Clinical Language Models
por: Abdullahi, Tassallah, et al.
Publicado: (2026)

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

Situated Natural Language Explanations
por: Zhu, Zining, et al.
Publicado: (2023)

Large Language Model based Situational Dialogues for Second Language Learning
por: Xu, Shuyao, et al.
Publicado: (2024)

Can Large Language Models abstract Medical Coded Language?
por: Lee, Simon A., et al.
Publicado: (2024)

Targeted Syntactic Evaluation of Language Models on Georgian Case Alignment
por: Gallagher, Daniel, et al.
Publicado: (2026)

PersonaLens: A Benchmark for Personalization Evaluation in Conversational AI Assistants
por: Zhao, Zheng, et al.
Publicado: (2025)

SignBind-LLM: Multi-Stage Modality Fusion for Sign Language Translation
por: Thomas, Marshall, et al.
Publicado: (2025)

EHRmonize: A Framework for Medical Concept Abstraction from Electronic Health Records using Large Language Models
por: Matos, João, et al.
Publicado: (2024)

Improving Language Model Personas via Rationalization with Psychological Scaffolds
por: Joshi, Brihi, et al.
Publicado: (2025)

Evaluating Large Language Model Biases in Persona-Steered Generation
por: Liu, Andy, et al.
Publicado: (2024)

Large Language Models as Misleading Assistants in Conversation
por: Hou, Betty Li, et al.
Publicado: (2024)

CFBenchmark: Chinese Financial Assistant Benchmark for Large Language Model
por: Lei, Yang, et al.
Publicado: (2023)

Attribute or Abstain: Large Language Models as Long Document Assistants
por: Buchmann, Jan, et al.
Publicado: (2024)

On Linear Representations and Pretraining Data Frequency in Language Models
por: Merullo, Jack, et al.
Publicado: (2025)

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

A Large-Language-Model Framework for Automated Humanitarian Situation Reporting
por: Decostanzi, Ivan, et al.
Publicado: (2025)

Probing Persona-Dependent Preferences in Language Models
por: Gilg, Oscar, et al.
Publicado: (2026)

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