Learn Before
Concept

Fine-tuning on Longer Sequences for Enhanced Length Extrapolation

A targeted and effective method for improving a pre-trained LLM's length extrapolation capabilities is to fine-tune it on a dataset of sequences that are longer than those used in its initial training phase.

0

1

Updated 2025-10-06

Contributors are:

Who are from:

Tags

Ch.3 Prompting - Foundations of Large Language Models

Foundations of Large Language Models

Foundations of Large Language Models Course

Computing Sciences