RT @matanabudy: 📄 New paper: "A Minimum Description Length Approach to Regularization in Neural Networks" with Orr Well, Emmanuel Chemla, @….

RT @DariaLioub: 📢Paper release📢.What computation is the Transformer performing in the layers after the top-1 becomes fixed (a so called "sa….

RT @GiliLior: Exciting news! I'll present my poster at #ACL2024 about unsupervised document structure extraction tomorrow (Aug. 12th) at 12….

The dynamic we capture, where the intermediate answers seem to be significant in the reasoning process, offers a novel cognitive approach for modeling together association and explicit reasoning. This also offers fresh insights into what "thinking" means in the context of AI.

We modeled this transition using a linear regression model, which demonstrates the transformation between the two semantic categories. Our findings indicate a strong connection between the intermediate and final answers categories.

We show that during the process of compositional questions, the middle layers of the network activate a subset of intermediate answers (dashed lines). Following this, a phase transition occurs, decreasing this activation while activating possible final answers (solid lines).

Consider the question: "What is the first letter of the color of a banana?". Did you think or say "yellow" before answering? Our analyses show that when answering, LLMs execute parallel reasoning paths by projecting a semantic set of tokens (colors) into another (letters).

🧠🤖 How do LLMs think? What kind of thought processes can emerge from artificial intelligence? Our latest paper about multi-hop reasoning tasks reveals some new interesting insights. Check out this thread for more details! @GoldsteinYAriel @amir_feder

RT @GiliLior: 🧠🤖 Does learning in the brain inherently require plasticity? In our latest paper we question this assumption, by leveraging i….