Towards Human-Level Book-Writing Capability

TL;DR

This paper introduces a novel dataset and training framework for long-form creative writing with language models, aiming to produce more human-like literary texts by hierarchical planning and fine-tuning.

Contribution

It presents a prompt-to-book generation approach using hierarchical summaries to improve the quality and human-likeness of AI-generated fiction.

Findings

Model trained on prompt-to-book trajectories produces more stylistically diverse stories.

Hierarchical planning improves the structural coherence of generated books.

Training on human-authored fiction enhances literary quality of outputs.

Abstract

Large language models optimized for instruction following and agentic tasks remain poorly aligned with the requirements of high-quality creative writing. Fiction frequently depends on behaviors that assistant-tuned models are explicitly trained to avoid, particularly deception, moral ambiguity, and unreliable narration. As a result, generated stories often appear structurally correct while remaining stylistically generic, overly explanatory, or weakly grounded in human literary behavior. We present a dataset construction and training framework for book-scale creative writing that reframes supervised fine-tuning as a prompt-to-book generation task grounded in human-authored fiction. Starting from public-domain novels, we derive a multi-resolution planning scaffold by summarizing each book at progressively finer levels, from a high-level premise to chapter- and scene-level structure. We then invert this hierarchy during training: the model learns to expand a prompt into increasingly detailed plans and finally into the original human-authored book text. This formulation preserves human prose as the final supervised target while using intermediate summaries to make book-scale generation learnable. We train a long-context language model on these prompt-to-book trajectories and study whether this objective shifts generation away from assistant-style prose and toward human literary writing.