A Hybrid Multi-Agent Prompting Approach for Simplifying Complex Sentences
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_ | 1866911008773111808 |
|---|---|
| author | Zunjare, Pratibha Hsiao, Michael |
| author_facet | Zunjare, Pratibha Hsiao, Michael |
| contents | This paper addresses the challenge of transforming complex sentences into sequences of logical, simplified sentences while preserving semantic and logical integrity with the help of Large Language Models. We propose a hybrid approach that combines advanced prompting with multi-agent architectures to enhance the sentence simplification process. Experimental results show that our approach was able to successfully simplify 70% of the complex sentences written for video game design application. In comparison, a single-agent approach attained a 48% success rate on the same task. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_11681 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Hybrid Multi-Agent Prompting Approach for Simplifying Complex Sentences Zunjare, Pratibha Hsiao, Michael Computation and Language This paper addresses the challenge of transforming complex sentences into sequences of logical, simplified sentences while preserving semantic and logical integrity with the help of Large Language Models. We propose a hybrid approach that combines advanced prompting with multi-agent architectures to enhance the sentence simplification process. Experimental results show that our approach was able to successfully simplify 70% of the complex sentences written for video game design application. In comparison, a single-agent approach attained a 48% success rate on the same task. |
| title | A Hybrid Multi-Agent Prompting Approach for Simplifying Complex Sentences |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2506.11681 |