arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2410.01637cs.CLcs.LG
收藏

关于将Unlimiformer适配到仅解码器Transformer的研究

On The Adaptation of Unlimiformer for Decoder-Only Transformers

Microsoft(微软)

Kian Ahrabian, Alon Benhaim, Barun Patra, Jay Pujara, Saksham Singhal, Xia Song

AI总结:

本文研究将Unlimiformer向量检索增强方法适配到仅解码器Transformer,通过一系列修改克服其不兼容问题,并在摘要生成、自由形式问答和指令微调模型上验证了有效性。

摘要:

当前大型语言模型面临的一个突出问题是其有限的上下文长度。近期专有模型如GPT-4和Claude 2分别引入了8k/32k和100k的更长上下文长度;然而,尽管社区做出了努力,大多数常见模型(如LLama-2)的上下文长度仍为4k或更短。Unlimiformer(Bertsch et al., 2023)是近期流行的一种向量检索增强方法,它将交叉注意力计算卸载到kNN索引上。但其主要局限在于无法开箱即用地兼容仅解码器Transformer。在本工作中,我们探讨了将Unlimiformer适配到仅解码器Transformer的实际考量,并提出了一系列修改以克服这一局限。此外,我们扩展了原有的摘要生成实验设置,加入了新任务(即自由形式问答)和一个经过指令微调的模型(即一个定制的6.7B GPT模型)。我们的结果展示了这些修改在摘要生成任务上的有效性,其性能与具有2倍上下文长度的模型相当。此外,我们还讨论了自由形式问答和指令微调模型的局限性及未来方向。

英文摘要:

One of the prominent issues stifling the current generation of large language models is their limited context length. Recent proprietary models such as GPT-4 and Claude 2 have introduced longer context lengths, 8k/32k and 100k, respectively; however, despite the efforts in the community, most common models, such as LLama-2, have a context length of 4k or less. Unlimiformer (Bertsch et al., 2023) is a recently popular vector-retrieval augmentation method that offloads cross-attention computations to a kNN index. However, its main limitation is incompatibility with decoder-only transformers out of the box. In this work, we explore practical considerations of adapting Unlimiformer to decoder-only transformers and introduce a series of modifications to overcome this limitation. Moreover, we expand the original experimental setup on summarization to include a new task (i.e., free-form Q&A) and an instruction-tuned model (i.e., a custom 6.7B GPT model). Our results showcase the effectiveness of these modifications on summarization, performing on par with a model with 2x the context length. Moreover, we discuss limitations and future directions for free-form Q&A and instruction-tuned models.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑