---
license: apache-2.0
datasets:
- HarlynDN/WebCiteS
language:
- zh
base_model: google/mt5-large
pipeline_tag: text2text-generation
---

This is the fine-tuned claim-split model based on mt5-large, described in the paper: [WebCiteS: Attributed Query-Focused Summarization on Chinese Web Search Results with Citations](https://aclanthology.org/2024.acl-long.806/)

The claim-split model receives a sentence and generates a list of its sub-claims. Please refer to the [GitHub repo](https://github.com/HarlynDN/WebCiteS) for exemplar usage.