arxiv
PublishedJune 29, 2026 at 4:00 AM
—neutral
Low-Agreeableness Persona Conditioning for Safe LLM Fine-Tuning
Publisher summary· verbatim
arXiv:2606.27709v1 Announce Type: cross Abstract: Recent work has shown that fine-tuning large language models (LLMs) for social warmth degrades factual reliability and increases sycophancy. We investigate a related but distinct failure mode: warmth fine-tuning also weakens adversarial safety, makin
Stay posted· Newsletter
A 5-min weekly brief — top movers, price watch, story of the week.
Discussion
No replies yet. Be first.
Related coverage
More from ARXIV
arxivA Consensus-Based Framework for Relative Preference Evaluation of Large Language Models26marxivHumanly: A Configurable and Traceable Environment for Human-AI Collaborative Writing26marxivProbing Latent Colombian Identity Inferences in Qwen2.5-7B with Natural Language Autoencoders26marxivKhondo: A Multimodal Benchmark for Document Packet Splitting of Bangla Forms26mThe Bubble Brief
WEEKLYRead safety insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗