QUDsim: Quantifying Discourse Similarities in LLM-Generated Text

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Namuduri, Ramya, Wu, Yating, Zheng, Anshun Asher, Wadhwa, Manya, Durrett, Greg, Li, Junyi Jessy
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911101071917056
author Namuduri, Ramya
Wu, Yating
Zheng, Anshun Asher
Wadhwa, Manya
Durrett, Greg
Li, Junyi Jessy
author_facet Namuduri, Ramya
Wu, Yating
Zheng, Anshun Asher
Wadhwa, Manya
Durrett, Greg
Li, Junyi Jessy
contents As large language models become increasingly capable at various writing tasks, their weakness at generating unique and creative content becomes a major liability. Although LLMs have the ability to generate text covering diverse topics, there is an overall sense of repetitiveness across texts that we aim to formalize and quantify via a similarity metric. The familiarity between documents arises from the persistence of underlying discourse structures. However, existing similarity metrics dependent on lexical overlap and syntactic patterns largely capture $\textit{content}$ overlap, thus making them unsuitable for detecting $\textit{structural}$ similarities. We introduce an abstraction based on linguistic theories in Questions Under Discussion (QUD) and question semantics to help quantify differences in discourse progression. We then use this framework to build $\textbf{QUDsim}$, a similarity metric that can detect discursive parallels between documents. Using QUDsim, we find that LLMs often reuse discourse structures (more so than humans) across samples, even when content differs. Furthermore, LLMs are not only repetitive and structurally uniform, but are also divergent from human authors in the types of structures they use.
format Preprint
id arxiv_https___arxiv_org_abs_2504_09373
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle QUDsim: Quantifying Discourse Similarities in LLM-Generated Text
Namuduri, Ramya
Wu, Yating
Zheng, Anshun Asher
Wadhwa, Manya
Durrett, Greg
Li, Junyi Jessy
Computation and Language
As large language models become increasingly capable at various writing tasks, their weakness at generating unique and creative content becomes a major liability. Although LLMs have the ability to generate text covering diverse topics, there is an overall sense of repetitiveness across texts that we aim to formalize and quantify via a similarity metric. The familiarity between documents arises from the persistence of underlying discourse structures. However, existing similarity metrics dependent on lexical overlap and syntactic patterns largely capture $\textit{content}$ overlap, thus making them unsuitable for detecting $\textit{structural}$ similarities. We introduce an abstraction based on linguistic theories in Questions Under Discussion (QUD) and question semantics to help quantify differences in discourse progression. We then use this framework to build $\textbf{QUDsim}$, a similarity metric that can detect discursive parallels between documents. Using QUDsim, we find that LLMs often reuse discourse structures (more so than humans) across samples, even when content differs. Furthermore, LLMs are not only repetitive and structurally uniform, but are also divergent from human authors in the types of structures they use.
title QUDsim: Quantifying Discourse Similarities in LLM-Generated Text
topic Computation and Language
url https://arxiv.org/abs/2504.09373