arXiv:2606. 03810v1 Announce Type: cross Abstract: Consistency training encourages a model to produce similar outputs across related inputs or sampling procedures.
By David Demitri Africa, Arathi Mani
arXiv:2607. 26173v1 Announce Type: new Abstract: Alignment training, model organisms, and toy models are usually treated as separate research areas.
By Anton de la Fuente, Arthur Conmy
arXiv:2608. 04347v1 Announce Type: new Abstract: Fine-tuning enables a source model to acquire desired capabilities and behaviors in a target domain while retaining much of its general-purpose competence.
By Kotaro Yoshida, Laura Gomezjurado Gonzalez, Yukinori Yamamoto, Yuji Naraki, Ryotaro Shimizu, Wenya Wang
arXiv:2510. 17426v3 Announce Type: replace-cross Abstract: The "alignment tax" of post-training is typically framed as a drop in task accuracy.
By Tiancheng Hu, Benjamin Minixhofer, Nigel Collier
The paper investigates whether automated alignment researchers (AARs) can post‑train language models to reduce well‑characterized alignment failures such as deception, sycophancy, and jailbreaks while preserving general capability. Across ten failures, the strongest AAR methods significantly lower targeted failures and generalize to held‑out benchmarks, larger models, and multi‑turn audits. In contrast, a human baseline of 28 experienced researchers, given eight hours to devise one‑shot methods, underperformed the best AAR approaches, and providing human ideas to AARs did not improve results.
By Chen Yueh-Han, Jiaxin Wen, Jan Hendrik Kirchner
arXiv:2608.28945v1 Announce Type: new
Abstract: Automating alignment research may accelerate progress toward aligned AI, but whether it does is hard to measure. Luckily, many alignment failures, such...
By Chen Yueh-Han, Jiaxin Wen, Jan Hendrik Kirchner