Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2502.05084 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916603381153792 |
|---|---|
| author | Deng, Xiaoyu Zhang, Ye Guo, Tianmin Zhang, Yongzhe Kang, Zhengjian Yang, Hang |
| author_facet | Deng, Xiaoyu Zhang, Ye Guo, Tianmin Zhang, Yongzhe Kang, Zhengjian Yang, Hang |
| contents | The astonishing performance of large language models (LLMs) and their remarkable achievements in production and daily life have led to their widespread application in collaborative tasks. However, current large models face challenges such as hallucination and lack of specificity in content generation in vertical domain tasks. Inspired by the contrast and classification mechanisms in human cognitive processes, this paper constructs an adversarial learning-based prompt framework named ChallengeMe, which includes three cascaded solutions: generation prompts, evaluation prompts, and feedback optimization. In this process, we designed seven core optimization dimensions and set the threshold for adversarial learning. The results of mixed case studies on the text summarization task show that the proposed framework can generate more accurate and fluent text summaries compared to the current advanced mainstream LLMs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_05084 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ChallengeMe: An Adversarial Learning-enabled Text Summarization Framework Deng, Xiaoyu Zhang, Ye Guo, Tianmin Zhang, Yongzhe Kang, Zhengjian Yang, Hang Computation and Language Artificial Intelligence The astonishing performance of large language models (LLMs) and their remarkable achievements in production and daily life have led to their widespread application in collaborative tasks. However, current large models face challenges such as hallucination and lack of specificity in content generation in vertical domain tasks. Inspired by the contrast and classification mechanisms in human cognitive processes, this paper constructs an adversarial learning-based prompt framework named ChallengeMe, which includes three cascaded solutions: generation prompts, evaluation prompts, and feedback optimization. In this process, we designed seven core optimization dimensions and set the threshold for adversarial learning. The results of mixed case studies on the text summarization task show that the proposed framework can generate more accurate and fluent text summaries compared to the current advanced mainstream LLMs. |
| title | ChallengeMe: An Adversarial Learning-enabled Text Summarization Framework |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2502.05084 |