Grokking of Implicit Reasoning in Transformers: A Mechanistic Journey to the Edge of Generalization
–Neural Information Processing Systems
We study whether transformers can learn to implicitly reason over parametric knowledge, a skill that even the most capable language models struggle with.
Neural Information Processing Systems
Oct-10-2025, 13:03:16 GMT
- Country:
- Asia
- Indonesia > Bali (0.04)
- Middle East
- Jordan (0.04)
- UAE > Abu Dhabi Emirate
- Abu Dhabi (0.04)
- Singapore (0.04)
- Europe > United Kingdom
- England > Cambridgeshire > Cambridge (0.04)
- North America
- Canada > Ontario
- Toronto (0.04)
- United States > Ohio (0.04)
- Canada > Ontario
- Asia
- Genre:
- Research Report > Experimental Study (1.00)
- Technology: