·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Dave Eggers told OpenAI staff that ChatGPT was ‘silencing an entire generation’5h◆Kimi: Threat or menace?7h◆The apps, gadgets, and tools every reader needs14h◆Neil Rimer thinks the AI money is coming back out21h◆The Steering Budget: Examples beat Knobs22h◆Polestar: Drift-Aware Cache Calibration and Token Commitment for Efficient Inference of Diffusion LLMs22h◆RxBrain: Embodied Cognition Foundation Model with Joint Language-Visual Reasoning and Imagination22h◆HABIB_TAZ at SemEval-2026 Task 11: Disentangling Formal Logic from Content via Synthetic Training and Multi-Objective Optimization22h◆When a Verified World Model Still Loses: Play-Adequacy vs Prediction-Accuracy in LLM-Synthesized Code World Models22h◆SAGA: Schema-Aware Grounding for Agentic Text-to-SPARQL Generation22h◆ReasFlow: Assisting Reasoning-Centric Scientific Discovery in Applied Mathematics via a Knowledge-Based Multi-Agent System22h◆LBA: Textual Hard-Label Adversarial Attack under Low Query Budgets22h◆Eta Given Delta: Defining LLM Tool Efficiency With Marginal Tool Utility22h◆Simplicity Paradox: Debunking myths about prompting and datasets for LLM evaluation22h◆LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks22h◆OmniaBench: Benchmarking General AI Agents Across Diverse Scenarios22h◆When AI Blurs the Boundaries of Contribution: An Empirical Study of Authorship Calibration22h◆Digital Pantheon: Simulating and Auditing Coalition Formation with LLM Agents22h◆Inoculation Adapters: Improved Selective Generalization of Capabilities with Fewer Surprising Backdoors22h◆Large Audio Language Models for Spoofing-Aware Speaker Verification22h◆Dave Eggers told OpenAI staff that ChatGPT was ‘silencing an entire generation’5h◆Kimi: Threat or menace?7h◆The apps, gadgets, and tools every reader needs14h◆Neil Rimer thinks the AI money is coming back out21h◆The Steering Budget: Examples beat Knobs22h◆Polestar: Drift-Aware Cache Calibration and Token Commitment for Efficient Inference of Diffusion LLMs22h◆RxBrain: Embodied Cognition Foundation Model with Joint Language-Visual Reasoning and Imagination22h◆HABIB_TAZ at SemEval-2026 Task 11: Disentangling Formal Logic from Content via Synthetic Training and Multi-Objective Optimization22h◆When a Verified World Model Still Loses: Play-Adequacy vs Prediction-Accuracy in LLM-Synthesized Code World Models22h◆SAGA: Schema-Aware Grounding for Agentic Text-to-SPARQL Generation22h◆ReasFlow: Assisting Reasoning-Centric Scientific Discovery in Applied Mathematics via a Knowledge-Based Multi-Agent System22h◆LBA: Textual Hard-Label Adversarial Attack under Low Query Budgets22h◆Eta Given Delta: Defining LLM Tool Efficiency With Marginal Tool Utility22h◆Simplicity Paradox: Debunking myths about prompting and datasets for LLM evaluation22h◆LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks22h◆OmniaBench: Benchmarking General AI Agents Across Diverse Scenarios22h◆When AI Blurs the Boundaries of Contribution: An Empirical Study of Authorship Calibration22h◆Digital Pantheon: Simulating and Auditing Coalition Formation with LLM Agents22h◆Inoculation Adapters: Improved Selective Generalization of Capabilities with Fewer Surprising Backdoors22h◆Large Audio Language Models for Spoofing-Aware Speaker Verification22h◆
News/Persona Cartography: Charting Language Model Personality Traits in Weight Space
arxiv
PublishedJuly 10, 2026 at 4:00 AM
—neutral

Persona Cartography: Charting Language Model Personality Traits in Weight Space

Source
arxiv.orgfull article ↗
Read on arxiv→
Publisher summary· verbatim

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 sp

Stay posted· Newsletter

A 5-min weekly brief — top movers, price watch, story of the week.

// no spam · unsubscribe one-click · free forever

Discussion
Source
↗
arxiv
Read original ↗All from arxiv →
Tags
04
#safety#personality#benchmark#research

No replies yet. Be first.

Source
↗
arxiv
Read original ↗All from arxiv →
Tags
04
#safety#personality#benchmark#research

Related coverage

More from ARXIV
arxivThe Steering Budget: Examples beat Knobs22harxivPolestar: Drift-Aware Cache Calibration and Token Commitment for Efficient Inference of Diffusion LLMs22harxivRxBrain: Embodied Cognition Foundation Model with Joint Language-Visual Reasoning and Imagination22harxivHABIB_TAZ at SemEval-2026 Task 11: Disentangling Formal Logic from Content via Synthetic Training and Multi-Objective Optimization22h
The Bubble Brief
WEEKLY

Read safety insights every Tuesday — top movers, new releases, story of the week.

// no spam · unsubscribe one-click · free forever

Originally published on arxiv ↗
HomeModelsNews