big-five

Tag

Cards List
#big-five

Do AI Personas Grow? Analyzing and Benchmarking Personality Evolution in LLM Agents After Life Events

Hugging Face Daily Papers · 2026-08-06 Cached

This paper studies how LLM agents' personalities evolve after major life events, using Big Five traits and introducing a benchmark called BFI-Adapt to evaluate the fidelity of event-induced personality changes across 14 models.

0 favorites 0 likes
#big-five

Misalignment Has a Personality: A Big Five Account of Emergent Misalignment

arXiv cs.CL · 2026-07-30 Cached

This paper introduces personality vectors for the Big Five traits extracted from language models to provide an interpretable account of emergent misalignment. It shows that misaligned fine-tuning shifts a model's personality along a specific signature (low agreeableness and conscientiousness, high extraversion and neuroticism), offering a human-readable diagnostic profile for safety phenomena.

0 favorites 0 likes
#big-five

How Affect Propagates among LLM Agents: Emergent Emotional Contagion in Crowd Simulation

arXiv cs.AI · 2026-07-29 Cached

This paper presents a multi-agent crowd simulation using LLM-driven agents that perceive and appraise each other through visual, auditory, and tactile channels, leading to emergent emotional contagion without explicit hand-authored affect transfer. The study demonstrates spatial, temporal, and personality-dependent contagion dynamics across five scenarios and evaluates backend-dependent appraisal behavior.

0 favorites 0 likes
#big-five

Mechanistic Personality Analysis of LLMs Steering Personality via Latent Feature Interventions

arXiv cs.AI · 2026-06-30 Cached

This paper introduces a mechanistic interpretability approach to steer LLM personality traits by identifying and intervening on latent features using sparse autoencoders, achieving controllable personality modulation while maintaining language performance.

0 favorites 0 likes
#big-five

Evaluation Drift in LLM Personality Induction: Are We Moving the Goalpost?

arXiv cs.CL · 2026-05-19 Cached

This paper investigates whether fine-tuning LLMs on long-form essays with associated Big Five personality profiles stabilizes questionnaire responses and can induce target profiles, finding that while variance reduces, accuracy on the full five-dimensional profile remains near chance.

0 favorites 0 likes
← Back to home

Submit Feedback