arxivJul 18
arXiv:2606.30252v2 Announce Type: replace Abstract: Inoculation prompting is a selective-generalization technique used against Emergent Misalignment. We introduce inoculation adapters (IA), a family of methods that similarly reduce the optimization pressure to learn undesired traits by strengthening
arxivMay 8
arXiv:2605.05436v1 Announce Type: cross Abstract: Deep learning systems are known to exhibit implicit regularization (alt. implicit bias), favoring simple solutions instead of merely minimizing the loss function. In some cases, we can analytically derive the implicit regularization -- connecting it
arxivApr 21bullish
arXiv:2510.10959v3 Announce Type: replace-cross Abstract: Reasoning ability has become a defining capability of Large Language Models (LLMs), with Reinforcement Learning with Verifiable Rewards (RLVR) emerging as a key paradigm to enhance it. However, RLVR training often suffers from policy entropy