Lei Huang, Rui Zhang, Xishan Zhang, Shaoli Liu, Tianshi Chen, Shaohui Peng, Jiaming Guo, Guanhua He
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
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. Ex 3 initially extract 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 Ex 3 's ability to produce higher-quality long-form novels.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2408.08506")
get_code_for_paper("2408.08506")
have("2408.08506")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2408.08506.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2408.08506)
Connect an agent — have() is free.