OmniThink: Expanding Knowledge Boundaries in Machine Writing through Thinking

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Xi, Zekun, Yin, Wenbiao, Fang, Jizhan, Wu, Jialong, Fang, Runnan, Jiang, Yong, Xie, Pengjun, Huang, Fei, Chen, Huajun, Zhang, Ningyu
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917093354504192
author Xi, Zekun
Yin, Wenbiao
Fang, Jizhan
Wu, Jialong
Fang, Runnan
Jiang, Yong
Xie, Pengjun
Huang, Fei
Chen, Huajun
Zhang, Ningyu
author_facet Xi, Zekun
Yin, Wenbiao
Fang, Jizhan
Wu, Jialong
Fang, Runnan
Jiang, Yong
Xie, Pengjun
Huang, Fei
Chen, Huajun
Zhang, Ningyu
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2501_09751
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle OmniThink: Expanding Knowledge Boundaries in Machine Writing through Thinking
Xi, Zekun
Yin, Wenbiao
Fang, Jizhan
Wu, Jialong
Fang, Runnan
Jiang, Yong
Xie, Pengjun
Huang, Fei
Chen, Huajun
Zhang, Ningyu
Computation and Language
Artificial Intelligence
Human-Computer Interaction
Information Retrieval
Machine Learning
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.
title OmniThink: Expanding Knowledge Boundaries in Machine Writing through Thinking
topic Computation and Language
Artificial Intelligence
Human-Computer Interaction
Information Retrieval
Machine Learning
url https://arxiv.org/abs/2501.09751