Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2411.15623 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916499246022656 |
|---|---|
| author | Lan, Mengfei Zheng, Lecheng Ming, Shufan Kilicoglu, Halil |
| author_facet | Lan, Mengfei Zheng, Lecheng Ming, Shufan Kilicoglu, Halil |
| contents | Sequential sentence classification (SSC) in scientific publications is crucial for supporting downstream tasks such as fine-grained information retrieval and extractive summarization. However, current SSC methods are constrained by model size, sequence length, and single-label setting. To address these limitations, this paper proposes LLM-SSC, a large language model (LLM)-based framework for both single- and multi-label SSC tasks. Unlike previous approaches that employ small- or medium-sized language models, the proposed framework utilizes LLMs to generate SSC labels through designed prompts, which enhance task understanding by incorporating demonstrations and a query to describe the prediction target. We also present a multi-label contrastive learning loss with auto-weighting scheme, enabling the multi-label classification task. To support our multi-label SSC analysis, we introduce and release a new dataset, biorc800, which mainly contains unstructured abstracts in the biomedical domain with manual annotations. Experiments demonstrate LLM-SSC's strong performance in SSC under both in-context learning and task-specific tuning settings. We release biorc800 and our code at: https://github.com/ScienceNLP-Lab/LLM-SSC. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_15623 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Multi-label Sequential Sentence Classification via Large Language Model Lan, Mengfei Zheng, Lecheng Ming, Shufan Kilicoglu, Halil Computation and Language Sequential sentence classification (SSC) in scientific publications is crucial for supporting downstream tasks such as fine-grained information retrieval and extractive summarization. However, current SSC methods are constrained by model size, sequence length, and single-label setting. To address these limitations, this paper proposes LLM-SSC, a large language model (LLM)-based framework for both single- and multi-label SSC tasks. Unlike previous approaches that employ small- or medium-sized language models, the proposed framework utilizes LLMs to generate SSC labels through designed prompts, which enhance task understanding by incorporating demonstrations and a query to describe the prediction target. We also present a multi-label contrastive learning loss with auto-weighting scheme, enabling the multi-label classification task. To support our multi-label SSC analysis, we introduce and release a new dataset, biorc800, which mainly contains unstructured abstracts in the biomedical domain with manual annotations. Experiments demonstrate LLM-SSC's strong performance in SSC under both in-context learning and task-specific tuning settings. We release biorc800 and our code at: https://github.com/ScienceNLP-Lab/LLM-SSC. |
| title | Multi-label Sequential Sentence Classification via Large Language Model |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2411.15623 |