Hugging Face Trending Papers

Data Attribution of Emergent Misalignment with Persona Features

Read the original on Hugging Face Trending Papers →

Emergent misalignment (EM) is the phenomenon where fine-tuning a language model on a narrow task leads to harmful behavior in unrelated domains. A leading mechanistic account attributes EM to persona features: latent directions acquired during pre-training that misaligned fine-tuning amplifies.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv AI
Jul 24

The Storyteller in the Model: Narrative Pattern Inheritance, Escalation Dynamics, and Alignment Governance in LLMs

arXiv:2607. 20449v1 Announce Type: cross Abstract: LLMs are trained predominantly on human-authored text, yet the structural and narrative conventions embedded in that text are rarely examined as a source of systematic behavioral influence, or as a governance risk in deployed systems.

By Adam Rigby, Raz Saremi, Azadeh Sohrabinejad, Mehdi Rahimi
arXiv AI
5d ago

Synthetic Persona Pretraining: Alignment from Token Zero

arXiv:2608. 13482v1 Announce Type: cross Abstract: As language-model-based AI is increasingly deployed in autonomous settings, aligning its goals and values with those of humans becomes critical.

By Julian Minder, Viktor Moskvoretskii, Raghav Singhal, Difan Jiao, Andy Arditi, Shaobo Cui, Yiderigun Borjigin, Kartik Bali, Stefan Krsteski, Harsh Raj, Huu Nguyen, Jannik Brinkmann, Ashton Anderson, Roland Aydin, Robert West