@inproceedings{zou-etal-2026-text,
title = "Text-Preserving Lossy Text Compression: A Study of Strategic Deletion and {LLM} Reconstruction",
author = "Zou, Yuchun and
Tong, Junhong and
Li, Jun",
editor = "Zhang, Yue and
Xu, Ruifeng and
Purwarianti, Ayu and
Rong, Tong and
Suzuki, Jun",
booktitle = "Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the {A}sia-Pacific Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.aacl-long.107/",
pages = "2349--2382",
ISBN = "979-8-89176-439-2",
abstract = "Traditional lossless text compression preserves every byte, but its gains on natural language are often modest. We study lossy semantic text compression, where the encoder strategically deletes parts of the text and a large language model (LLM) reconstructs the original from the retained skeleton. We benchmark a progression of deletion strategies, from character-level and word-level rules driven by word length or corpus frequency to surprisal-based and hybrid rules that require a neural encoder, and reach three findings. First, deletion by corpus word frequency is a strong low-cost baseline: a static frequency lookup remains competitive with far more expensive semantic methods. Second, semantic and hybrid methods gain most at mild-to-moderate compression, whereas at the lowest retention rate frequency-based deletion matches them and keeps more named entities. Third, QLoRA fine-tuning yields a compact local decoder that, once adapted, is competitive with zero-shot Gemini 2.0 Flash. Additional English and Chinese experiments show that the framework transfers across domains, while the best deletion rule remains dataset-dependent."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zou-etal-2026-text">
<titleInfo>
<title>Text-Preserving Lossy Text Compression: A Study of Strategic Deletion and LLM Reconstruction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuchun</namePart>
<namePart type="family">Zou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junhong</namePart>
<namePart type="family">Tong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayu</namePart>
<namePart type="family">Purwarianti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Rong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-439-2</identifier>
</relatedItem>
<abstract>Traditional lossless text compression preserves every byte, but its gains on natural language are often modest. We study lossy semantic text compression, where the encoder strategically deletes parts of the text and a large language model (LLM) reconstructs the original from the retained skeleton. We benchmark a progression of deletion strategies, from character-level and word-level rules driven by word length or corpus frequency to surprisal-based and hybrid rules that require a neural encoder, and reach three findings. First, deletion by corpus word frequency is a strong low-cost baseline: a static frequency lookup remains competitive with far more expensive semantic methods. Second, semantic and hybrid methods gain most at mild-to-moderate compression, whereas at the lowest retention rate frequency-based deletion matches them and keeps more named entities. Third, QLoRA fine-tuning yields a compact local decoder that, once adapted, is competitive with zero-shot Gemini 2.0 Flash. Additional English and Chinese experiments show that the framework transfers across domains, while the best deletion rule remains dataset-dependent.</abstract>
<identifier type="citekey">zou-etal-2026-text</identifier>
<location>
<url>https://aclanthology.org/2026.aacl-long.107/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>2349</start>
<end>2382</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Text-Preserving Lossy Text Compression: A Study of Strategic Deletion and LLM Reconstruction
%A Zou, Yuchun
%A Tong, Junhong
%A Li, Jun
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-439-2
%F zou-etal-2026-text
%X Traditional lossless text compression preserves every byte, but its gains on natural language are often modest. We study lossy semantic text compression, where the encoder strategically deletes parts of the text and a large language model (LLM) reconstructs the original from the retained skeleton. We benchmark a progression of deletion strategies, from character-level and word-level rules driven by word length or corpus frequency to surprisal-based and hybrid rules that require a neural encoder, and reach three findings. First, deletion by corpus word frequency is a strong low-cost baseline: a static frequency lookup remains competitive with far more expensive semantic methods. Second, semantic and hybrid methods gain most at mild-to-moderate compression, whereas at the lowest retention rate frequency-based deletion matches them and keeps more named entities. Third, QLoRA fine-tuning yields a compact local decoder that, once adapted, is competitive with zero-shot Gemini 2.0 Flash. Additional English and Chinese experiments show that the framework transfers across domains, while the best deletion rule remains dataset-dependent.
%U https://aclanthology.org/2026.aacl-long.107/
%P 2349-2382
Markdown (Informal)
[Text-Preserving Lossy Text Compression: A Study of Strategic Deletion and LLM Reconstruction](https://aclanthology.org/2026.aacl-long.107/) (Zou et al., AACL-IJCNLP 2026)
ACL