← all papers · overview

XL3M: A Training-free Framework For LLM Length Extension Based On Segment-wise Inference

Abstract

Length generalization failure problem, namely the large language model (LLM) fails to generalize to texts longer than its maximum training length, greatly restricts the application of LLM in the scenarios with streaming long inputs. To address this problem, the existing methods either require substantial costs or introduce precision loss. In this paper, we empirically find that the accuracy of the

Related papers

Ranked by semantic similarity — how closely each paper's abstract matches this one (100% = near-identical topic).