@inproceedings{xu-xu-2026-benchmarking,
title = "Benchmarking Argument Identification and Ellipsis Recovery in {C}hinese Comparative Constructions",
author = "Xu, Wenjing and
Xu, Hongzhi",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.1489/",
doi = "10.18653/2026.findings-emnlp.1489",
pages = "31694--31707",
ISBN = "979-8-89176-462-0",
abstract = "Ellipsis in comparative constructions provides a challenging test of semantic interpretation because comprehenders must reconstruct implicit constituents that are not overtly expressed. This study investigates whether large language models (LLMs) can capture the structured semantic inferences required for understanding Chinese comparative constructions. We introduce a linguistically motivated evaluation framework targeting two essential components of comparative interpretation: (i) identification of comparative arguments and (ii) recovery of elliptical constituents. Based on 2,076 naturally occurring Chinese bi-comparative sentences, we construct an annotated resource with comparative argument boundaries, recovered elliptical constituents, and five comparison dimensions representing distinct semantic bases of comparison. We evaluate several representative LLMs, including DeepSeek-V3.1, GPT-4o, and Gemini-2.0-Flash. While all models reliably identify overt comparative arguments, they exhibit substantial degradation when reconstructing implicit constituents. These results suggest that current LLMs can capture surface-level structural regularities but still face challenges in recovering implicit semantic representations required for human-like interpretation. Our resource provides a controlled linguistic testbed for studying the relationship between linguistic structure, semantic inference, and computational models of language understanding."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xu-xu-2026-benchmarking">
<titleInfo>
<title>Benchmarking Argument Identification and Ellipsis Recovery in Chinese Comparative Constructions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wenjing</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongzhi</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Ellipsis in comparative constructions provides a challenging test of semantic interpretation because comprehenders must reconstruct implicit constituents that are not overtly expressed. This study investigates whether large language models (LLMs) can capture the structured semantic inferences required for understanding Chinese comparative constructions. We introduce a linguistically motivated evaluation framework targeting two essential components of comparative interpretation: (i) identification of comparative arguments and (ii) recovery of elliptical constituents. Based on 2,076 naturally occurring Chinese bi-comparative sentences, we construct an annotated resource with comparative argument boundaries, recovered elliptical constituents, and five comparison dimensions representing distinct semantic bases of comparison. We evaluate several representative LLMs, including DeepSeek-V3.1, GPT-4o, and Gemini-2.0-Flash. While all models reliably identify overt comparative arguments, they exhibit substantial degradation when reconstructing implicit constituents. These results suggest that current LLMs can capture surface-level structural regularities but still face challenges in recovering implicit semantic representations required for human-like interpretation. Our resource provides a controlled linguistic testbed for studying the relationship between linguistic structure, semantic inference, and computational models of language understanding.</abstract>
<identifier type="citekey">xu-xu-2026-benchmarking</identifier>
<identifier type="doi">10.18653/2026.findings-emnlp.1489</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.1489/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>31694</start>
<end>31707</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Benchmarking Argument Identification and Ellipsis Recovery in Chinese Comparative Constructions
%A Xu, Wenjing
%A Xu, Hongzhi
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F xu-xu-2026-benchmarking
%X Ellipsis in comparative constructions provides a challenging test of semantic interpretation because comprehenders must reconstruct implicit constituents that are not overtly expressed. This study investigates whether large language models (LLMs) can capture the structured semantic inferences required for understanding Chinese comparative constructions. We introduce a linguistically motivated evaluation framework targeting two essential components of comparative interpretation: (i) identification of comparative arguments and (ii) recovery of elliptical constituents. Based on 2,076 naturally occurring Chinese bi-comparative sentences, we construct an annotated resource with comparative argument boundaries, recovered elliptical constituents, and five comparison dimensions representing distinct semantic bases of comparison. We evaluate several representative LLMs, including DeepSeek-V3.1, GPT-4o, and Gemini-2.0-Flash. While all models reliably identify overt comparative arguments, they exhibit substantial degradation when reconstructing implicit constituents. These results suggest that current LLMs can capture surface-level structural regularities but still face challenges in recovering implicit semantic representations required for human-like interpretation. Our resource provides a controlled linguistic testbed for studying the relationship between linguistic structure, semantic inference, and computational models of language understanding.
%R 10.18653/2026.findings-emnlp.1489
%U https://aclanthology.org/2026.findings-emnlp.1489/
%U https://doi.org/10.18653/2026.findings-emnlp.1489
%P 31694-31707
Markdown (Informal)
[Benchmarking Argument Identification and Ellipsis Recovery in Chinese Comparative Constructions](https://aclanthology.org/2026.findings-emnlp.1489/) (Xu & Xu, Findings 2026)
ACL