papers
SepSeq: A Training-Free Framework for Long Numerical Sequence Processing in LLMs
arXiv cs.CL·2mo ago·1 min read
Authors:Jie Sun, Yu Liu, Lu Han, Qiwen Deng, Xiang Shu, Yang Xiao, Xingyu Lu, Jun Zhou, Pengfei Liu, Lintao Ma, Jiancan Wu, Xiang Wang
Abstract:While transformer-based Large Language Models (LLMs) theoretically support massive context windows, they suffer from severe performance degradation when processing long numerical sequences. We attribute this failure to the attention dispersion in the Softmax mechanism, which prevents the model from concentrating attention. To overcome this, we propose Separate Sequence (SepSeq), a training-free, plug-and-play framework to mitigate dispersion by strategically inserting separator tokens. Mechanistically, we demonstrate that separator tokens act as an attention sink, recalibrating attention to focus on local segments while preserving global context. Extensive evaluations on 9 widely-adopted LLMs confirm the effectiveness of our approach: SepSeq yields an average relative accuracy improvement of 35.6% across diverse domains while reducing total inference token consumption by 16.4% on average.
Submission history
From: Jie Sun [view email]
[v1]
Thu, 9 Apr 2026 02:40:34 UTC (821 KB)