@inproceedings{tanaka-ishii-2026-repeated,
title = "Repeated Sequences Reveal Gaps between Large Language Models and Natural Language",
author = "Tanaka-Ishii, Kumiko",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-long.379/",
pages = "8367--8382",
ISBN = "979-8-89176-390-6",
abstract = "Evaluating whether large language models (LLMs) capture the structureof natural language beyond local fluency remains an open challenge.Existing evaluation methods, largely based on task performance orshort-context behavior, provide limited insight into the long-rangestatistical organization of generated text.We propose a complementary evaluation framework based on repeatedsubsequences. By analyzing their distribution across scales andrelating it to higher-order R{\'e}nyi entropies, we probe how textsreuse previously established structure under finite-lengthconditions. Experiments on human-written texts and length-matchedGPT-generated texts show that,while power-law models can describerestricted ranges of block length, the observed entropy growth isoften equally or better characterized by logarithmic{--}power forms.Across datasets, natural language exhibits stable entropy-growthpatterns over accessible ranges, with consistent average behavior despite variability across individual texts. In contrast,GPT-generated texts show systematic and statistically significantshifts in estimated exponents with model size.These results demonstrate that repeated-subsequence entropyprovides a quantitative structural diagnostic that revealssystematic differences in long-range organization,distinguishing natural language from state-of-the-art LLM outputsbeyond surface-level fluency."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tanaka-ishii-2026-repeated">
<titleInfo>
<title>Repeated Sequences Reveal Gaps between Large Language Models and Natural Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kumiko</namePart>
<namePart type="family">Tanaka-Ishii</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-390-6</identifier>
</relatedItem>
<abstract>Evaluating whether large language models (LLMs) capture the structureof natural language beyond local fluency remains an open challenge.Existing evaluation methods, largely based on task performance orshort-context behavior, provide limited insight into the long-rangestatistical organization of generated text.We propose a complementary evaluation framework based on repeatedsubsequences. By analyzing their distribution across scales andrelating it to higher-order Rényi entropies, we probe how textsreuse previously established structure under finite-lengthconditions. Experiments on human-written texts and length-matchedGPT-generated texts show that,while power-law models can describerestricted ranges of block length, the observed entropy growth isoften equally or better characterized by logarithmic–power forms.Across datasets, natural language exhibits stable entropy-growthpatterns over accessible ranges, with consistent average behavior despite variability across individual texts. In contrast,GPT-generated texts show systematic and statistically significantshifts in estimated exponents with model size.These results demonstrate that repeated-subsequence entropyprovides a quantitative structural diagnostic that revealssystematic differences in long-range organization,distinguishing natural language from state-of-the-art LLM outputsbeyond surface-level fluency.</abstract>
<identifier type="citekey">tanaka-ishii-2026-repeated</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.379/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>8367</start>
<end>8382</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Repeated Sequences Reveal Gaps between Large Language Models and Natural Language
%A Tanaka-Ishii, Kumiko
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F tanaka-ishii-2026-repeated
%X Evaluating whether large language models (LLMs) capture the structureof natural language beyond local fluency remains an open challenge.Existing evaluation methods, largely based on task performance orshort-context behavior, provide limited insight into the long-rangestatistical organization of generated text.We propose a complementary evaluation framework based on repeatedsubsequences. By analyzing their distribution across scales andrelating it to higher-order Rényi entropies, we probe how textsreuse previously established structure under finite-lengthconditions. Experiments on human-written texts and length-matchedGPT-generated texts show that,while power-law models can describerestricted ranges of block length, the observed entropy growth isoften equally or better characterized by logarithmic–power forms.Across datasets, natural language exhibits stable entropy-growthpatterns over accessible ranges, with consistent average behavior despite variability across individual texts. In contrast,GPT-generated texts show systematic and statistically significantshifts in estimated exponents with model size.These results demonstrate that repeated-subsequence entropyprovides a quantitative structural diagnostic that revealssystematic differences in long-range organization,distinguishing natural language from state-of-the-art LLM outputsbeyond surface-level fluency.
%U https://aclanthology.org/2026.acl-long.379/
%P 8367-8382
Markdown (Informal)
[Repeated Sequences Reveal Gaps between Large Language Models and Natural Language](https://aclanthology.org/2026.acl-long.379/) (Tanaka-Ishii, ACL 2026)
ACL