SepSeq improves LLM accuracy on long numerical sequences by an average of 35.6% by inserting separator tokens that serve as attention sinks while cutting token usage by 16.4%.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SepSeq: A Training-Free Framework for Long Numerical Sequence Processing in LLMs
SepSeq improves LLM accuracy on long numerical sequences by an average of 35.6% by inserting separator tokens that serve as attention sinks while cutting token usage by 16.4%.