用闭源大模型直接生成论文参考文献，无需训练即可上榜。
LLM-Powered Ensemble Learning for Paper Source Tracing: A GPU-Free Approach
- 用闭源大模型零样本生成参考文献，不依赖微调
- 通过集成学习提升预测准确率，获竞赛第三名
- 唯一不需GPU训练的获奖方案，适合资源受限场景
我们参加了KDD CUP 2024论文来源追溯竞赛并获得第三名。该任务要求识别给定学术论文的参考文献来源（即参赛方定义的ref-sources）。与多数团队采用BERT或ChatGLM等预训练模型微调的方法不同，我们的主要方法是使用闭源大语言模型（LLMs）。随着大语言模型技术的发展，闭源模型在零样本或少样本场景下已具备处理复杂推理任务的能力。因此，在无GPU条件下，我们直接利用闭源大模型从论文内容生成预测的参考文献，并进一步通过集成学习优化结果。值得注意的是，我们的方法是所有获奖方案中唯一不需要使用GPU进行模型训练的。代码已公开于https://github.com/Cklwanfifa/KDDCUP2024-PST。
原文摘要 · Abstract (English)
We participated in the KDD CUP 2024 paper source tracing competition and achieved the 3rd place. This competition tasked participants with identifying the reference sources (i.e., ref-sources, as referred to by the organizers of the competition) of given academic papers. Unlike most teams that addressed this challenge by fine-tuning pre-trained neural language models such as BERT or ChatGLM, our primary approach utilized closed-source large language models (LLMs). With recent advancements in LLM technology, closed-source LLMs have demonstrated the capability to tackle complex reasoning tasks in zero-shot or few-shot scenarios. Consequently, in the absence of GPUs, we employed closed-source LLMs to directly generate predicted reference sources from the provided papers. We further refined these predictions through ensemble learning. Notably, our method was the only one among the award-winning approaches that did not require the use of GPUs for model training. Code available at https://github.com/Cklwanfifa/KDDCUP2024-PST.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。