Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2408.08506 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909302002810880 |
|---|---|
| author | Huang, Lei Guo, Jiaming He, Guanhua Zhang, Xishan Zhang, Rui Peng, Shaohui Liu, Shaoli Chen, Tianshi |
| author_facet | Huang, Lei Guo, Jiaming He, Guanhua Zhang, Xishan Zhang, Rui Peng, Shaohui Liu, Shaoli Chen, Tianshi |
| contents | Generating long-term texts such as novels using artificial intelligence has always been a challenge. A common approach is to use large language models (LLMs) to construct a hierarchical framework that first plans and then writes. Despite the fact that the generated novels reach a sufficient length, they exhibit poor logical coherence and appeal in their plots and deficiencies in character and event depiction, ultimately compromising the overall narrative quality. In this paper, we propose a method named Extracting Excelsior and Expanding. Ex3 initially extracts structure information from raw novel data. By combining this structure information with the novel data, an instruction-following dataset is meticulously crafted. This dataset is then utilized to fine-tune the LLM, aiming for excelsior generation performance. In the final stage, a tree-like expansion method is deployed to facilitate the generation of arbitrarily long novels. Evaluation against previous methods showcases Ex3's ability to produce higher-quality long-form novels. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_08506 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Ex3: Automatic Novel Writing by Extracting, Excelsior and Expanding Huang, Lei Guo, Jiaming He, Guanhua Zhang, Xishan Zhang, Rui Peng, Shaohui Liu, Shaoli Chen, Tianshi Computation and Language Artificial Intelligence Generating long-term texts such as novels using artificial intelligence has always been a challenge. A common approach is to use large language models (LLMs) to construct a hierarchical framework that first plans and then writes. Despite the fact that the generated novels reach a sufficient length, they exhibit poor logical coherence and appeal in their plots and deficiencies in character and event depiction, ultimately compromising the overall narrative quality. In this paper, we propose a method named Extracting Excelsior and Expanding. Ex3 initially extracts structure information from raw novel data. By combining this structure information with the novel data, an instruction-following dataset is meticulously crafted. This dataset is then utilized to fine-tune the LLM, aiming for excelsior generation performance. In the final stage, a tree-like expansion method is deployed to facilitate the generation of arbitrarily long novels. Evaluation against previous methods showcases Ex3's ability to produce higher-quality long-form novels. |
| title | Ex3: Automatic Novel Writing by Extracting, Excelsior and Expanding |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2408.08506 |