@inproceedings{kim-etal-2026-text,
title = "From Text to Structure: The {PACK}a{GE} Benchmark for Bidirectional Causal Reasoning in Paragraphs and Graphs",
author = "Kim, Juhyeon and
Lee, Dohun and
Jang, Jiwon and
Shim, Joseph and
Park, Hyunwoo",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.27/",
pages = "585--611",
ISBN = "979-8-89176-459-0",
abstract = "Large Language Models (LLMs) have demonstrated remarkable capabilities across various domains, yet they struggle with causal reasoning tasks. We introduce PACKaGE (Paragraph-level Annotated Causal Knowledge and Graph{--}tExt), a causal benchmark dataset that pairs paragraph-level texts with explicit causal graphs. Unlike prior sentence-level resources, our benchmark dataset (i) operates at paragraph level to capture various and interdependent causal pathways; (ii) offers multimodal annotations including full graphs and contextualized relations; and (iii) maps extended passages to comprehensive graphs. We detail a four-stage construction pipeline: collecting causality-labeled and fact-centric texts, inducing graphs from span-tagged pairs, condensing nodes, and recomposing path-aligned narratives. Overall, the paired evaluation highlights a persistent discrepancy between linguistic competence and causal understanding in LLMs, pointing to the need for further development."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-etal-2026-text">
<titleInfo>
<title>From Text to Structure: The PACKaGE Benchmark for Bidirectional Causal Reasoning in Paragraphs and Graphs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Juhyeon</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dohun</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiwon</namePart>
<namePart type="family">Jang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Shim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hyunwoo</namePart>
<namePart type="family">Park</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>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</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">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Large Language Models (LLMs) have demonstrated remarkable capabilities across various domains, yet they struggle with causal reasoning tasks. We introduce PACKaGE (Paragraph-level Annotated Causal Knowledge and Graph–tExt), a causal benchmark dataset that pairs paragraph-level texts with explicit causal graphs. Unlike prior sentence-level resources, our benchmark dataset (i) operates at paragraph level to capture various and interdependent causal pathways; (ii) offers multimodal annotations including full graphs and contextualized relations; and (iii) maps extended passages to comprehensive graphs. We detail a four-stage construction pipeline: collecting causality-labeled and fact-centric texts, inducing graphs from span-tagged pairs, condensing nodes, and recomposing path-aligned narratives. Overall, the paired evaluation highlights a persistent discrepancy between linguistic competence and causal understanding in LLMs, pointing to the need for further development.</abstract>
<identifier type="citekey">kim-etal-2026-text</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.27/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>585</start>
<end>611</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T From Text to Structure: The PACKaGE Benchmark for Bidirectional Causal Reasoning in Paragraphs and Graphs
%A Kim, Juhyeon
%A Lee, Dohun
%A Jang, Jiwon
%A Shim, Joseph
%A Park, Hyunwoo
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F kim-etal-2026-text
%X Large Language Models (LLMs) have demonstrated remarkable capabilities across various domains, yet they struggle with causal reasoning tasks. We introduce PACKaGE (Paragraph-level Annotated Causal Knowledge and Graph–tExt), a causal benchmark dataset that pairs paragraph-level texts with explicit causal graphs. Unlike prior sentence-level resources, our benchmark dataset (i) operates at paragraph level to capture various and interdependent causal pathways; (ii) offers multimodal annotations including full graphs and contextualized relations; and (iii) maps extended passages to comprehensive graphs. We detail a four-stage construction pipeline: collecting causality-labeled and fact-centric texts, inducing graphs from span-tagged pairs, condensing nodes, and recomposing path-aligned narratives. Overall, the paired evaluation highlights a persistent discrepancy between linguistic competence and causal understanding in LLMs, pointing to the need for further development.
%U https://aclanthology.org/2026.emnlp-main.27/
%P 585-611
Markdown (Informal)
[From Text to Structure: The PACKaGE Benchmark for Bidirectional Causal Reasoning in Paragraphs and Graphs](https://aclanthology.org/2026.emnlp-main.27/) (Kim et al., EMNLP 2026)
ACL