🧠
Intelligence Artificielle
Think in Latent, Explain in Language: Self-Explainable Latent Reasoning
arXiv:2608.13570v1 Announce Type: new Abstract: Latent reasoning has emerged as a powerful alternative to text-based Chain-of-Thought (CoT), offering significant gains in computational efficiency by compressing verbose reasoning into compact embeddings. However, compressing reasoning into the latent space renders the thinking opaque, hindering its interpretability. Current…
Lire l'article