Understanding Survey Paper Taxonomy about Large Language Models via Graph Representation Learning
This work addresses the challenge for researchers in synthesizing the growing volume of LLM survey papers, though it is incremental as it applies existing graph representation learning techniques to a new domain-specific task.
The authors tackled the problem of automatically classifying numerous survey papers on Large Language Models (LLMs) into a taxonomy, developing a method that uses graph structure information to outperform language model-based approaches and achieve performance above average human recognition levels.
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.