Understanding Survey Paper Taxonomy about Large Language Models via Graph Representation Learning
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913235657031680 |
|---|---|
| author | Zhuang, Jun Kennington, Casey |
| author_facet | Zhuang, Jun Kennington, Casey |
| contents | As new research on Large Language Models (LLMs) continues, it is difficult to keep up with new research and models. To help researchers synthesize the new research many have written survey papers, but even those have become numerous. In this paper, we develop a method to automatically assign survey papers to a taxonomy. We collect the metadata of 144 LLM survey papers and explore three paradigms to classify papers within the taxonomy. Our work indicates that leveraging graph structure information on co-category graphs can significantly outperform the language models in two paradigms; pre-trained language models' fine-tuning and zero-shot/few-shot classifications using LLMs. We find that our model surpasses an average human recognition level and that fine-tuning LLMs using weak labels generated by a smaller model, such as the GCN in this study, can be more effective than using ground-truth labels, revealing the potential of weak-to-strong generalization in the taxonomy classification task. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_10409 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Understanding Survey Paper Taxonomy about Large Language Models via Graph Representation Learning Zhuang, Jun Kennington, Casey Computation and Language Artificial Intelligence Information Retrieval Machine Learning As new research on Large Language Models (LLMs) continues, it is difficult to keep up with new research and models. To help researchers synthesize the new research many have written survey papers, but even those have become numerous. In this paper, we develop a method to automatically assign survey papers to a taxonomy. We collect the metadata of 144 LLM survey papers and explore three paradigms to classify papers within the taxonomy. Our work indicates that leveraging graph structure information on co-category graphs can significantly outperform the language models in two paradigms; pre-trained language models' fine-tuning and zero-shot/few-shot classifications using LLMs. We find that our model surpasses an average human recognition level and that fine-tuning LLMs using weak labels generated by a smaller model, such as the GCN in this study, can be more effective than using ground-truth labels, revealing the potential of weak-to-strong generalization in the taxonomy classification task. |
| title | Understanding Survey Paper Taxonomy about Large Language Models via Graph Representation Learning |
| topic | Computation and Language Artificial Intelligence Information Retrieval Machine Learning |
| url | https://arxiv.org/abs/2402.10409 |