LLM-Powered Ensemble Learning for Paper Source Tracing: A GPU-Free Approach
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913503241043968 |
|---|---|
| author | Chen, Kunlong Wang, Junjun Chen, Zhaoqun Chen, Kunjin Chen, Yitian |
| author_facet | Chen, Kunlong Wang, Junjun Chen, Zhaoqun Chen, Kunjin Chen, Yitian |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_09383 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | LLM-Powered Ensemble Learning for Paper Source Tracing: A GPU-Free Approach Chen, Kunlong Wang, Junjun Chen, Zhaoqun Chen, Kunjin Chen, Yitian Machine Learning Artificial Intelligence Computation and Language 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. |
| title | LLM-Powered Ensemble Learning for Paper Source Tracing: A GPU-Free Approach |
| topic | Machine Learning Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2409.09383 |