arXiv AI
Activation Steering with Jungian Cognitive Functions
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Jul 24
The Geometry of Personality: Activation Steering with Jungian Cognitive Functions
arXiv:2607. 20803v1 Announce Type: cross Abstract: Activation steering enables control and interpretation of LLMs, yet existing work primarily models personality through static trait frameworks such as the Big Five.
arXiv AI
Jul 10
Persona Cartography: Charting Language Model Personality Traits in Weight Space
arXiv:2607. 07916v1 Announce Type: new Abstract: Large language models exhibit recurring behavioural patterns -- personas -- that shape generalisation and safety, but we lack reliable tools for decomposing, measuring, and controlling them.
arXiv AI
Aug 28
Do LLMs Understand Personality? Rethinking Persona Fidelity Evaluation through Structured Behavioral Inference
The paper introduces PRISM, a new framework for evaluating how well large language models (LLMs) maintain persona fidelity in dynamic dialogue. PRISM reframes the task as a structured inverse inference problem grounded in Systemic Functional Linguistics, breaking persona fidelity into Task Framing, Interpersonal Stance, and Linguistic Style dimensions. Experiments demonstrate that PRISM produces more accurate and stable judgments than existing holistic or static psychometric methods, offering a more reliable and auditable evaluation process.
arXiv Computation and Language
Oct 27
FATE-5: Faithful Alignment of Trait Expression for Continuous Big Five Personality Control
arXiv:2610.34889v1 Announce Type: new Abstract: Controlling personality in large language models is important for building conversational agents that can be customized to different users and interact...
arXiv AI
Jul 28
Do LLMs Experience an Internal Polylogue? Investigating Reasoning through the Lens of Personas
arXiv:2605. 09159v2 Announce Type: replace Abstract: Recent work shows that large language models (LLMs) encode behavioral traits ("personas") as linear directions in activation space, often called "persona vectors".
arXiv Computer Vision
Aug 25
Traits Run Deeper: Trait-Specific Asymmetric Fusion for Personality Assessment
arXiv:2606.11269v2 Announce Type: replace Abstract: Personality assessment aims to infer stable traits from dynamic behaviors across modalities like language, voice, and facial expressions. Existing...