mlsanityData to 14 Oct 2026

Identifying and Manipulating Personality Traits in LLMs Through Activation Engineering

arXiv 2412.10427 ↗First posted 10 Dec 2024cs.CL cs.AIcited by 14

Not on the map. Why?

Abstract (arXiv)

The field of large language models (LLMs) has grown rapidly in recent years, driven by the desire for better efficiency, interpretability, and safe use. Building on the novel approach of "activation engineering," this study explores personality modification in LLMs, drawing inspiration from research like Refusal in LLMs Is Mediated by a Single Direction (arXiv:2406.11717) and Steering Llama 2 via Contrastive Activation Addition (arXiv:2312.06681). We leverage activation engineering to develop a method for identifying and adjusting activation directions related to personality traits, which may allow for dynamic LLM personality fine-tuning. This work aims to further our understanding of LLM interpretability while examining the ethical implications of such developments.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Builds on 9 of its 14 references that are in the map. First posted on arXiv 10 Dec 2024.

Builds on

9 of 14 references.

References · 9

  1. 2022Locating and Editing Factual Associations in GPTcited by 2,691
  2. 2023Steering Llama 2 via Contrastive Activation Additioncited by 1,085
  3. 2022Mass-Editing Memory in a Transformercited by 1,001
  4. 2023PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traitscited by 234
  5. 2022Extracting Latent Steering Vectors from Pretrained Language Modelscited by 225
  6. 2023Personality Traits in Large Language Modelscited by 169
  7. 2017What do Neural Machine Translation Models Learn about Morphology?cited by 166
  8. 2023SteerLM: Attribute Conditioned SFT as an (User-Steerable) Alternative to RLHFcited by 111
  9. 2024Self-assessment, Exhibition, and Recognition: a Review of Personality in Large Language Modelscited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 9.

14 papers.

Sort:

By area:

  1. 2025Humanizing LLMs: A Survey of Psychological Measurements with Tools, Datasets, and Human-Agent Applicationscited by 10
  2. 2025Linear Personality Probing and Steering in LLMs: A Big Five Studycited by 9
  3. 2025Activation-Space Personality Steering: Hybrid Layer Selection for Stable Trait Control in LLMscited by 5
  4. 2026Steering at the Source: Style Modulation Heads for Robust Persona Controlcited by 5
  5. 2025Neural Transparency: Mechanistic Interpretability Interfaces for Anticipating Model Behaviors for Personalized AIcited by 3
  6. 2026Understanding Parents' Desires in Moderating Children's Interactions with GenAI Chatbots through LLM-Generated Probescited by 2
  7. 2025Steerable Chatbots: Exploring Personalization Control Interfaces via LLM Activation Steeringcited by 1
  8. 2026Enhancing Large Language Models for Time-Series Forecasting via Vector-Injected In-Context Learningcited by 1
  9. 2026Psychological Steering of Large Language Modelscited by 1
  10. 2026Your LLM, Your Style: Behavioral Mode Axes for LLM Behavioral Controlcited by 1
  11. 2026Facet-Level Persona Control by Trait-Activated Routing with Contrastive SAE for Role-Playing LLMscited by 0
  12. 2026Survive at All Costs: Exploring LLM's Risky Behaviors under Survival Pressurecited by 0
2 more
  1. 2026Intrinsic Guardrails: How Semantic Geometry of Personality Interacts with Emergent Misalignment in LLMscited by 0
  2. 2026The Geometry of Personality: Activation Steering with Jungian Cognitive Functionscited by 0