cd /news/artificial-intelligence/persona-cartography-charting-languag… · home topics artificial-intelligence article
[ARTICLE · art-53629] src=arxiv.org ↗ pub= topic=artificial-intelligence verified=true sentiment=· neutral

Persona Cartography: Charting Language Model Personality Traits in Weight Space

Researchers introduced a method to map and control personality traits in large language models using the OCEAN framework. By training low-rank adapters to amplify or suppress traits like neuroticism and agreeableness, they demonstrated monotonic trait control, additive composition, and effects on safety-relevant behaviors across six models. The work bridges personality measurement, model editing, and AI safety.

read1 min views1 publishedJul 10, 2026

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. Our central insight is to treat personas as positions in a space of behavioural traits, using the OCEAN framework to describe model personas in terms of Openness, Conscientiousness, Extraversion, Agreeableness, and Neuroticism. We train low-rank adapters to amplify or suppress individual traits, and evaluate their effects using an LLM-judge calibrated against a human-validated panel, trait-specific multiple-choice benchmarks, and standard capability evaluations. Across six models from three families (4B-32B), we find that each adapter moves its target trait largely monotonically with scale, combines approximately additively with other adapters to construct mixed personas, and preserves performance on capability benchmarks at moderate scales. We further show that the induced trait axes affect safety-relevant behaviour in downstream evaluations: for example, moving along neuroticism and agreeableness axes affects frustration and sycophancy respectively. We also introduce an unsupervised psychometric pipeline that recovers four interpretable behavioural factors (tone, initiative, didacticism, epistemic caution) from model rollouts. Persona control can then be considered in terms of learning, scaling, and composing traits in weight space, providing a bridge between personality measurement, model editing, and safety.

── more in #artificial-intelligence 4 stories · sorted by recency
── more on @arxiv 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/persona-cartography-…] indexed:0 read:1min 2026-07-10 ·