Showing cs.LGShow all
2 papers · 1 filter
cs.LG2024
Position Coupling: Improving Length Generalization of Arithmetic Transformers Using Task Structure
Hanseul Cho, Jaeyoung Cha, Pranjal Awasthi +3
Even for simple arithmetic tasks like integer addition, it is challenging for Transformers to generalize to longer sequences than those encountered during training. To tackle this…
cs.LG2023
Improving Length-Generalization in Transformers via Task Hinting
Pranjal Awasthi, Anupam Gupta
It has been observed in recent years that transformers have problems with length generalization for certain types of reasoning and arithmetic tasks. In particular, the performance…