ZeroDL: Zero-shot Distribution Learning for Text Clustering via Large Language Models
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916783196209152 |
|---|---|
| author | Jo, Hwiyeol Lee, Hyunwoo Yoo, Kang Min Park, Taiwoo |
| author_facet | Jo, Hwiyeol Lee, Hyunwoo Yoo, Kang Min Park, Taiwoo |
| contents | The advancements in large language models (LLMs) have brought significant progress in NLP tasks. However, if a task cannot be fully described in prompts, the models could fail to carry out the task. In this paper, we propose a simple yet effective method to contextualize a task toward a LLM. The method utilizes (1) open-ended zero-shot inference from the entire dataset, (2) aggregate the inference results, and (3) finally incorporate the aggregated meta-information for the actual task. We show the effectiveness in text clustering tasks, empowering LLMs to perform text-to-text-based clustering and leading to improvements on several datasets. Furthermore, we explore the generated class labels for clustering, showing how the LLM understands the task through data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_13342 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ZeroDL: Zero-shot Distribution Learning for Text Clustering via Large Language Models Jo, Hwiyeol Lee, Hyunwoo Yoo, Kang Min Park, Taiwoo Computation and Language Artificial Intelligence The advancements in large language models (LLMs) have brought significant progress in NLP tasks. However, if a task cannot be fully described in prompts, the models could fail to carry out the task. In this paper, we propose a simple yet effective method to contextualize a task toward a LLM. The method utilizes (1) open-ended zero-shot inference from the entire dataset, (2) aggregate the inference results, and (3) finally incorporate the aggregated meta-information for the actual task. We show the effectiveness in text clustering tasks, empowering LLMs to perform text-to-text-based clustering and leading to improvements on several datasets. Furthermore, we explore the generated class labels for clustering, showing how the LLM understands the task through data. |
| title | ZeroDL: Zero-shot Distribution Learning for Text Clustering via Large Language Models |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2406.13342 |