We trained a small transformer (100M params) for basic arithmetic. W. the right training data it nails 12x12 digits multiplication w/o CoT (that's 10^24 possibilities, so no it's not memorization🤣). Maybe arithmetic is not the LLM kryptonite after all?šŸ¤” https://t.co/dldvBhb2Qj

1 min read Original article ↗

arxiv.org

Positional Description Matters for Transformers Arithmetic

Transformers, central to the successes in modern Natural Language Processing, often falter on arithmetic tasks despite their vast capabilities --which paradoxically include remarkable coding...