AINeutralarXiv – CS AI · Feb 276/105
🧠
How Do Latent Reasoning Methods Perform Under Weak and Strong Supervision?
Researchers analyzed latent reasoning methods in AI, which perform multi-step reasoning in continuous latent spaces rather than textual spaces. The study reveals two key issues: pervasive shortcut behavior where models achieve high accuracy without actual latent reasoning, and a failure to implement structured search despite encoding multiple possibilities.