arXiv:2607. 04510v1 Announce Type: cross Abstract: Emergent misalignment (EM) -- the broad misbehaviour a language model acquires after fine-tuning on narrow harmful data -- is mediated in Qwen2.
By Lyndon Drake (University of Oxford), Zandi Eberstadt (University of Oxford)
arXiv:2606. 00545v1 Announce Type: new Abstract: Post-trained language models can recognize their own outputs from a sentence or two out of context.
By Asvin G
arXiv:2608. 11225v1 Announce Type: new Abstract: AI "personality clones" force a re-examination of personal identity in operational terms.
By Luc E. Brunet
arXiv:2605. 03160v2 Announce Type: replace Abstract: The standard protocol for interpreting sparse-autoencoder (SAE) features labels each feature from its top-activating contexts and validates the label by steering that single feature at a typical magnitude.
By Michael A. Riegler, Birk Sebastian Frostelid Torpmann-Hagen
arXiv:2607. 13162v1 Announce Type: cross Abstract: What a language model will and will not do is largely set during post-training, but which behaviors it expresses, hides, or resists is not revealed by prompting alone.
By Winston Zeng, Ali Emami, Jinho Choi
arXiv:2605. 07284v2 Announce Type: replace Abstract: A late-layer change learned during post-training may work on the base model's earlier state, or it may depend on earlier computation learned with it.
By Yifan Zhou