#artificial intelligence
Apr 2026
AtManRL: Towards Faithful Reasoning via Differentiable Attention Saliency
The results suggest that training explicitly for saliency is a promising route towards chain-of-thought reasoning that is more faithful to the model's actual decision process.
M. Höth, Kristian Kersting, Bjorn Deiseroth et al.
· arXiv.org · 1 citation