LLM-Powered Ensemble Learning for Paper Source Tracing: A GPU-Free Approach

TL;DR

This paper presents a GPU-free ensemble learning method using closed-source large language models to trace paper sources, achieving third place in a competitive academic paper source identification task.

Contribution

The approach leverages closed-source LLMs and ensemble techniques for source tracing without GPU training, differing from prior methods that relied on fine-tuning neural models.

Findings

Achieved third place in KDD CUP 2024 paper source tracing competition.

Did not require GPUs for model training, unlike other top methods.

Effective zero-shot reasoning with closed-source LLMs and ensemble learning.

Abstract

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.