Saltar al contenido

Últimas noticias

Hemeroteca →
¿Y si el 'no' de una IA no se quita con un simple interruptor?
Videojuegos

¿Y si el 'no' de una IA no se quita con un simple interruptor?

arXiv:2606.13720v1 Announce Type: new Abstract: Arditi et al. (2024) has shown that refusal in safety fine-tuned chat models is mediated by a single linear direction in the residual stream, recoverable by a difference-in-means (DiM) of harmful and harmless activations. We compare DiM-based interventions (activation addition and directional ablation) with two interventions derived from Iterative Nullspace Projection (INLP) -- nullspace projection and counterfactual flipping -- on five open-weigh

15/06/2026
Cuando la IA te saca la ficha: así personaliza sus conversaciones según tu perfil
Videojuegos

Cuando la IA te saca la ficha: así personaliza sus conversaciones según tu perfil

arXiv:2606.13683v1 Announce Type: new Abstract: To address the challenge that current dialogue policy planning methods struggle to dynamically adapt to diverse user characteristics, this paper proposes a User Portrait based Nested Rollout Policy Adaptation (UP-NRPA) online framework with Large Language Models. In contrast to conventional approaches dependent on model training and require offline reinforcement learning policy models for user groups, UP-NRPA enables dynamic customization of dialo

15/06/2026