OUNLP at TSAR 2025 Shared Task: Multi-Round Text Simplifier via Code Generation
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914254259486720 |
|---|---|
| author | Huynh, Cuong Cao, Jie |
| author_facet | Huynh, Cuong Cao, Jie |
| contents | This paper describes the OUNLP system submitted to the TSAR-2025 Shared Task (Alva-Manchego et al., 2025), designed for readability-controlled text simplification using LLM-prompting-based generation. Based on the analysis of prompt-based text simplification methods, we discovered an interesting finding that text simplification performance is highly related to the gap between the source CEFR (Arase et al., 2022) level and the target CEFR level. Inspired by this finding, we propose two multi-round simplification methods and generate them via GPT-4o: rule-based simplification (MRS-Rule) and jointly rule-based LLM simplification (MRS-Joint). Our submitted systems ranked 7 out of 20 teams. Later improvements with MRS-Joint show that taking the LLM simplified candidates as the starting point could further boost the multi-round simplification performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_04495 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | OUNLP at TSAR 2025 Shared Task: Multi-Round Text Simplifier via Code Generation Huynh, Cuong Cao, Jie Computation and Language Artificial Intelligence This paper describes the OUNLP system submitted to the TSAR-2025 Shared Task (Alva-Manchego et al., 2025), designed for readability-controlled text simplification using LLM-prompting-based generation. Based on the analysis of prompt-based text simplification methods, we discovered an interesting finding that text simplification performance is highly related to the gap between the source CEFR (Arase et al., 2022) level and the target CEFR level. Inspired by this finding, we propose two multi-round simplification methods and generate them via GPT-4o: rule-based simplification (MRS-Rule) and jointly rule-based LLM simplification (MRS-Joint). Our submitted systems ranked 7 out of 20 teams. Later improvements with MRS-Joint show that taking the LLM simplified candidates as the starting point could further boost the multi-round simplification performance. |
| title | OUNLP at TSAR 2025 Shared Task: Multi-Round Text Simplifier via Code Generation |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2511.04495 |