LongAlign: A Recipe for Long Context Alignment of Large Language Models
CoRR(2024)
摘要
Extending large language models to effectively handle long contexts requires
instruction fine-tuning on input sequences of similar length. To address this,
we present LongAlign – a recipe of the instruction data, training, and
evaluation for long context alignment. First, we construct a long
instruction-following dataset using Self-Instruct. To ensure the data
diversity, it covers a broad range of tasks from various long context sources.
Second, we adopt the packing and sorted batching strategies to speed up
supervised fine-tuning on data with varied length distributions. Additionally,
we develop a loss weighting method to balance the contribution to the loss
across different sequences during packing training. Third, we introduce the
LongBench-Chat benchmark for evaluating instruction-following capabilities on
queries of 10k-100k in length. Experiments show that LongAlign outperforms
existing recipes for LLMs in long context tasks by up to 30%, while also
maintaining their proficiency in handling short, generic tasks. The code, data,
and long-aligned models are open-sourced at https://github.com/THUDM/LongAlign.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要