Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
To See the Unseen: on the Generalization Ability of Transformers in Symbolic Reasoning
Nevena LaziÄ, Liam Fowl, András György +1
We investigate the ability of decoder-only transformer models to perform abstract symbolic reasoning; specifically solving propositional logic reasoning problems given in-context.…
cs.AI2025
Beyond Statistical Learning: Exact Learning Is Essential for General Intelligence
András György, Tor Lattimore, Nevena LaziÄ +1
Sound deductive reasoning -- the ability to derive new knowledge from existing facts and rules -- is an indisputably desirable aspect of general intelligence. Despite the major adv…