Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.17209 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911365223940096 |
|---|---|
| author | Moreno, Lourdes Sanchez-Gomez, Jesus M. Sanchez-Escudero, Marco Antonio Martínez, Paloma |
| author_facet | Moreno, Lourdes Sanchez-Gomez, Jesus M. Sanchez-Escudero, Marco Antonio Martínez, Paloma |
| contents | This paper describes the participation of HULAT-UC3M in CLEARS 2025 Subtask 1: Adaptation of Text to Plain Language (PL) in Spanish. We explored strategies based on models trained on Spanish texts, including a zero-shot configuration using prompt engineering and a fine-tuned version with Low-Rank Adaptation (LoRA). Different strategies were evaluated on representative internal subsets of the training data, using the official task metrics, cosine similarity (SIM) and the Fernández-Huerta readability index (FH) to guide the selection of the optimal model and prompt combination. The final system was selected for its balanced and consistent performance, combining normalization steps, the RigoChat-7B-v2 model, and a dedicated PL-oriented prompt. It ranked first in semantic similarity (SIM = 0.75), however, fourth in readability (FH = 69.72). We also discuss key challenges related to training data heterogeneity and the limitations of current evaluation metrics in capturing both linguistic clarity and content preservation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_17209 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Prompt-Based Simplification for Plain Language using Spanish Language Models Moreno, Lourdes Sanchez-Gomez, Jesus M. Sanchez-Escudero, Marco Antonio Martínez, Paloma Computation and Language This paper describes the participation of HULAT-UC3M in CLEARS 2025 Subtask 1: Adaptation of Text to Plain Language (PL) in Spanish. We explored strategies based on models trained on Spanish texts, including a zero-shot configuration using prompt engineering and a fine-tuned version with Low-Rank Adaptation (LoRA). Different strategies were evaluated on representative internal subsets of the training data, using the official task metrics, cosine similarity (SIM) and the Fernández-Huerta readability index (FH) to guide the selection of the optimal model and prompt combination. The final system was selected for its balanced and consistent performance, combining normalization steps, the RigoChat-7B-v2 model, and a dedicated PL-oriented prompt. It ranked first in semantic similarity (SIM = 0.75), however, fourth in readability (FH = 69.72). We also discuss key challenges related to training data heterogeneity and the limitations of current evaluation metrics in capturing both linguistic clarity and content preservation. |
| title | Prompt-Based Simplification for Plain Language using Spanish Language Models |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2509.17209 |