arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2408.16264cs.CLcs.AI
收藏

LoraMap:发挥LoRA连接的力量

LoraMap: Harnessing the Power of LoRA Connections

Seoul National University(首尔大学);Medical Research Center, Institute of Medical and Biological Engineering(医学与生物工程研究所医学研究中心)

Hyeryun Park, Jeongwon Kwak, Dongsuk Jang, Sumin Park, Jinwook Choi

AI总结:

本文提出LoraMap方法,通过在多个针对事实核查微调的LoRA之间建立连接映射,以更少的可训练参数优于现有的LoraHub和LoraConcat方法。

摘要:

事实核查技术可以缓解大型语言模型(LLMs)中的幻觉问题,这是专业领域中的一个突出问题。由于低秩适应(LoRA)等参数高效技术能够克服巨大的计算开销,一些研究探索了多个LoRA的集成。以往的研究侧重于并行集成,本文则研究了在多个LoRA之间建立连接的方法。我们创建了三个专为事实核查定制的推理数据集,并对各个LoRA进行微调,使其能够从多样化视角进行观察和推理。随后,我们探索了分配这些推理LoRA的策略,并提出了LoraMap,一种用于映射它们之间连接的方法。事实核查任务的结果表明,LoraMap的性能优于集成LoRA的现有方法LoraHub。与拼接LoRA并进一步微调的LoraConcat相比,LoraMap在可训练参数显著更少的情况下也表现更优。

英文摘要:

Fact-checking techniques can mitigate hallucinations in Large Language Models (LLMs), a prominent issue in specialized domains. As parameter-efficient techniques such as Low-Rank Adaptation (LoRA) can overcome substantial computational overhead, some studies have explored the integration of multiple LoRAs. While previous studies focus on parallel integration, this paper investigates methods to establish connections among multiple LoRAs. We create three reasoning datasets tailored to fact-checking and fine-tune individual LoRAs, allowing them to view and reason from diverse perspectives. Then, we explore strategies for allocating these reasoning LoRAs and introduce LoraMap, an approach to map connections between them. The results of the fact-checking task demonstrate that the performance of LoraMap is superior to LoraHub, an existing method for integrating LoRAs. LoraMap also outperforms with significantly fewer trainable parameters than LoraConcat, which concatenates LoRAs and further fine-tunes them.

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。

↑