@inproceedings{zhu-frank-2024-lieder,
title = "{LIEDER}: Linguistically-Informed Evaluation for Discourse Entity Recognition",
author = "Zhu, Xiaomeng and
Frank, Robert",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.luhme-long.746/",
doi = "10.18653/v1/2024.acl-long.746",
pages = "13835--13850",
abstract = "Discourse Entity (DE) recognition is the task of identifying novel and known entities introduced within a text. While previous work has found that large language models have basic, if imperfect, DE recognition abilities (Schuster and Linzen, 2022), it remains largely unassessed which of the fundamental semantic properties that govern the introduction and subsequent reference to DEs they have knowledge of. We propose the Linguistically-Informed Evaluation for Discourse Entity Recognition (LIEDER) dataset that allows for a detailed examination of language models' knowledge of four crucial semantic properties: existence, uniqueness, plurality, and novelty. We find evidence that state-of-the-art large language models exhibit sensitivity to all of these properties except novelty, which demonstrates that they have yet to reach human-level language understanding abilities."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhu-frank-2024-lieder">
<titleInfo>
<title>LIEDER: Linguistically-Informed Evaluation for Discourse Entity Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiaomeng</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="family">Frank</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Discourse Entity (DE) recognition is the task of identifying novel and known entities introduced within a text. While previous work has found that large language models have basic, if imperfect, DE recognition abilities (Schuster and Linzen, 2022), it remains largely unassessed which of the fundamental semantic properties that govern the introduction and subsequent reference to DEs they have knowledge of. We propose the Linguistically-Informed Evaluation for Discourse Entity Recognition (LIEDER) dataset that allows for a detailed examination of language models’ knowledge of four crucial semantic properties: existence, uniqueness, plurality, and novelty. We find evidence that state-of-the-art large language models exhibit sensitivity to all of these properties except novelty, which demonstrates that they have yet to reach human-level language understanding abilities.</abstract>
<identifier type="citekey">zhu-frank-2024-lieder</identifier>
<identifier type="doi">10.18653/v1/2024.acl-long.746</identifier>
<location>
<url>https://aclanthology.org/2024.luhme-long.746/</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>13835</start>
<end>13850</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LIEDER: Linguistically-Informed Evaluation for Discourse Entity Recognition
%A Zhu, Xiaomeng
%A Frank, Robert
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F zhu-frank-2024-lieder
%X Discourse Entity (DE) recognition is the task of identifying novel and known entities introduced within a text. While previous work has found that large language models have basic, if imperfect, DE recognition abilities (Schuster and Linzen, 2022), it remains largely unassessed which of the fundamental semantic properties that govern the introduction and subsequent reference to DEs they have knowledge of. We propose the Linguistically-Informed Evaluation for Discourse Entity Recognition (LIEDER) dataset that allows for a detailed examination of language models’ knowledge of four crucial semantic properties: existence, uniqueness, plurality, and novelty. We find evidence that state-of-the-art large language models exhibit sensitivity to all of these properties except novelty, which demonstrates that they have yet to reach human-level language understanding abilities.
%R 10.18653/v1/2024.acl-long.746
%U https://aclanthology.org/2024.luhme-long.746/
%U https://doi.org/10.18653/v1/2024.acl-long.746
%P 13835-13850
Markdown (Informal)
[LIEDER: Linguistically-Informed Evaluation for Discourse Entity Recognition](https://aclanthology.org/2024.luhme-long.746/) (Zhu & Frank, ACL 2024)
ACL