OmniThink: Expanding Knowledge Boundaries in Machine Writing through Thinking

TL;DR

OmniThink introduces a slow-thinking framework for machine writing that enhances knowledge depth and originality in generated articles by emulating human-like iterative expansion and reflection.

Contribution

It presents a novel slow-thinking approach that improves knowledge density and content quality in machine-generated long-form articles.

Findings

Enhanced knowledge density in generated articles

Maintained coherence and depth in outputs

Positive human and expert evaluations

Abstract

Machine writing with large language models often relies on retrieval-augmented generation. However, these approaches remain confined within the boundaries of the model's predefined scope, limiting the generation of content with rich information. Specifically, vanilla-retrieved information tends to lack depth, novelty, and suffers from redundancy, which negatively impacts the quality of generated articles, leading to shallow, unoriginal, and repetitive outputs. To address these issues, we propose OmniThink, a slow-thinking machine writing framework that emulates the human-like process of iterative expansion and reflection. The core idea behind OmniThink is to simulate the cognitive behavior of learners as they slowly deepen their knowledge of the topics. Experimental results demonstrate that OmniThink improves the knowledge density of generated articles without compromising metrics such as coherence and depth. Human evaluations and expert feedback further highlight the potential of OmniThink to address real-world challenges in the generation of long-form articles. Code is available at https://github.com/zjunlp/OmniThink.