Cover Image

Activation-Space Personality Steering: Hybrid Layer Selection for Stable Trait Control in LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Bhandari, Pranav, Fay, Nicolas, Selvaganapathy, Sanjeevan, Datta, Amitava, Naseem, Usman, Nasim, Mehwish
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Evaluating Personality Traits in Large Language Models: Insights from Psychological Questionnaires
by: Bhandari, Pranav, et al.
Published: (2025)

Do Personality Traits Interfere? Geometric Limitations of Steering in Large Language Models
by: Bhandari, Pranav, et al.
Published: (2026)

Can LLM Agents Maintain a Persona in Discourse?
by: Bhandari, Pranav, et al.
Published: (2025)

Do LLMs Use Cultural Knowledge Without Being Told? A Multilingual Evaluation of Implicit Pragmatic Adaptation
by: Nasim, Mehwish, et al.
Published: (2026)

Bias Beyond Borders: Political Ideology Evaluation and Steering in Multilingual LLMs
by: Nadeem, Afrozah, et al.
Published: (2026)

Confident, Calibrated, or Complicit: Safety Alignment and Ideological Bias in LLM Hate Speech Detection
by: Selvaganapathy, Sanjeeevan, et al.
Published: (2025)

Steering Towards Fairness: Mitigating Political Bias in LLMs
by: Nadeem, Afrozah, et al.
Published: (2025)

They Said Memes Were Harmless-We Found the Ones That Hurt: Decoding Jokes, Symbols, and Cultural References
by: Tripathi, Sahil, et al.
Published: (2026)

SafeConstellations: Mitigating Over-Refusals in LLMs Through Task-Aware Representation Steering
by: Maskey, Utsav, et al.
Published: (2025)

Steering Over-refusals Towards Safety in Retrieval Augmented Generation
by: Maskey, Utsav, et al.
Published: (2025)

Exploring the Personality Traits of LLMs through Latent Features Steering
by: Yang, Shu, et al.
Published: (2024)

Mechanistic Interpretability for Large Language Model Alignment: Progress, Challenges, and Future Directions
by: Naseem, Usman
Published: (2026)

Competing LLM Agents in a Non-Cooperative Game of Opinion Polarisation
by: Qasmi, Amin, et al.
Published: (2025)

Over-Refusal and Representation Subspaces: A Mechanistic Analysis of Task-Conditioned Refusal in Aligned LLMs
by: Maskey, Utsav, et al.
Published: (2026)

PersoPilot: An Adaptive AI-Copilot for Transparent Contextualized Persona Classification and Personalized Response Generation
by: Afzoon, Saleh, et al.
Published: (2026)

Fairness Evaluation and Inference Level Mitigation in LLMs
by: Nadeem, Afrozah, et al.
Published: (2025)

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

Framing Political Bias in Multilingual LLMs Across Pakistani Languages
by: Nadeem, Afrozah, et al.
Published: (2025)

Stable and Explainable Personality Trait Evaluation in Large Language Models with Internal Activations
by: Ma, Xiaoxu, et al.
Published: (2026)

PersoBench: Benchmarking Personalized Response Generation in Large Language Models
by: Afzoon, Saleh, et al.
Published: (2024)

We Think, Therefore We Align LLMs to Helpful, Harmless and Honest Before They Go Wrong
by: Kashyap, Gautam Siddharth, et al.
Published: (2025)

Can Reasoning LLMs Enhance Clinical Document Classification?
by: Mustafa, Akram, et al.
Published: (2025)

VISPA: Pluralistic Alignment via Automatic Value Selection and Activation
by: Zheng, Shenyan, et al.
Published: (2026)

Evaluating Hierarchical Clinical Document Classification Using Reasoning-Based LLMs
by: Mustafa, Akram, et al.
Published: (2025)

Personalized Text Generation with Contrastive Activation Steering
by: Zhang, Jinghao, et al.
Published: (2025)

Guiding Giants: Lightweight Controllers for Weighted Activation Steering in LLMs
by: Hegazy, Amr, et al.
Published: (2025)

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering
by: Li, Yichen, et al.
Published: (2025)

Mitigating Memorization in LLMs using Activation Steering
by: Suri, Manan, et al.
Published: (2025)

Neural FOXP2 -- Language Specific Neuron Steering for Targeted Language Improvement in LLMs
by: Saha, Anusa, et al.
Published: (2026)

DUAL-Bench: Measuring Over-Refusal and Robustness in Vision-Language Models
by: Ren, Kaixuan, et al.
Published: (2025)

SHIELD: Classifier-Guided Prompting for Robust and Safer LVLMs
by: Ren, Juan, et al.
Published: (2025)

Benchmarking Large Language Models for Cryptanalysis and Side-Channel Vulnerabilities
by: Maskey, Utsav, et al.
Published: (2025)

Enhancing ESG Impact Type Identification through Early Fusion and Multilingual Models
by: Veeramani, Hariram, et al.
Published: (2024)

Should LLM Safety Be More Than Refusing Harmful Instructions?
by: Maskey, Utsav, et al.
Published: (2025)

Seeing the Threat: Vulnerabilities in Vision-Language Models to Adversarial Attack
by: Ren, Juan, et al.
Published: (2025)

Facet-Level Persona Control by Trait-Activated Routing with Contrastive SAE for Role-Playing LLMs
by: Tang, Wenqiu, et al.
Published: (2026)

Secret Keepers: The Impact of LLMs on Linguistic Markers of Personal Traits
by: Sourati, Zhivar, et al.
Published: (2024)

AlignCultura: Towards Culturally Aligned Large Language Models?
by: Kashyap, Gautam Siddharth, et al.
Published: (2026)

Too Helpful, Too Harmless, Too Honest or Just Right?
by: Kashyap, Gautam Siddharth, et al.
Published: (2025)

When the Model Said 'No Comment', We Knew Helpfulness Was Dead, Honesty Was Alive, and Safety Was Terrified
by: Kashyap, Gautam Siddharth, et al.
Published: (2026)