@inproceedings{tan-etal-2025-cascading,
title = "Cascading Large Language Models for Salient Event Graph Generation",
author = "Tan, Xingwei and
Zhou, Yuxiang and
Pergola, Gabriele and
He, Yulan",
editor = "Chiruzzo, Luis and
Ritter, Alan and
Wang, Lu",
booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = apr,
year = "2025",
address = "Albuquerque, New Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.naacl-long.112/",
doi = "10.18653/v1/2025.naacl-long.112",
pages = "2223--2245",
ISBN = "979-8-89176-189-6",
abstract = "Generating event graphs from long documents is challenging due to the inherent complexity of multiple tasks involved such as detecting events, identifying their relationships, and reconciling unstructured input with structured graphs. Recent studies typically consider all events with equal importance, failing to distinguish salient events crucial for understanding narratives. This paper presents CALLMSAE, a CAscading Large Language Model framework for SAlient Event graph generation, which leverages the capabilities of LLMs and eliminates the need for costly human annotations. We first identify salient events by prompting LLMs to generate summaries, from which salient events are identified. Next, we develop an iterative code refinement prompting strategy to generate event relation graphs, removing hallucinated relations and recovering missing edges. Powered by CALLMSAE, we present \textit{NYT-SEG}, a large-scale automatically annotated event graph dataset which can serve as distant supervision signals. Fine-tuning contextualised graph generation models on \textit{NYT-SEG} outperforms the models trained on CAEVO data. Results on a human-annotated test set show that the proposed method generates salient and more accurate graphs, outperforming competitive baselines."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tan-etal-2025-cascading">
<titleInfo>
<title>Cascading Large Language Models for Salient Event Graph Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xingwei</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuxiang</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriele</namePart>
<namePart type="family">Pergola</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, New Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-189-6</identifier>
</relatedItem>
<abstract>Generating event graphs from long documents is challenging due to the inherent complexity of multiple tasks involved such as detecting events, identifying their relationships, and reconciling unstructured input with structured graphs. Recent studies typically consider all events with equal importance, failing to distinguish salient events crucial for understanding narratives. This paper presents CALLMSAE, a CAscading Large Language Model framework for SAlient Event graph generation, which leverages the capabilities of LLMs and eliminates the need for costly human annotations. We first identify salient events by prompting LLMs to generate summaries, from which salient events are identified. Next, we develop an iterative code refinement prompting strategy to generate event relation graphs, removing hallucinated relations and recovering missing edges. Powered by CALLMSAE, we present NYT-SEG, a large-scale automatically annotated event graph dataset which can serve as distant supervision signals. Fine-tuning contextualised graph generation models on NYT-SEG outperforms the models trained on CAEVO data. Results on a human-annotated test set show that the proposed method generates salient and more accurate graphs, outperforming competitive baselines.</abstract>
<identifier type="citekey">tan-etal-2025-cascading</identifier>
<identifier type="doi">10.18653/v1/2025.naacl-long.112</identifier>
<location>
<url>https://aclanthology.org/2025.naacl-long.112/</url>
</location>
<part>
<date>2025-04</date>
<extent unit="page">
<start>2223</start>
<end>2245</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Cascading Large Language Models for Salient Event Graph Generation
%A Tan, Xingwei
%A Zhou, Yuxiang
%A Pergola, Gabriele
%A He, Yulan
%Y Chiruzzo, Luis
%Y Ritter, Alan
%Y Wang, Lu
%S Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2025
%8 April
%I Association for Computational Linguistics
%C Albuquerque, New Mexico
%@ 979-8-89176-189-6
%F tan-etal-2025-cascading
%X Generating event graphs from long documents is challenging due to the inherent complexity of multiple tasks involved such as detecting events, identifying their relationships, and reconciling unstructured input with structured graphs. Recent studies typically consider all events with equal importance, failing to distinguish salient events crucial for understanding narratives. This paper presents CALLMSAE, a CAscading Large Language Model framework for SAlient Event graph generation, which leverages the capabilities of LLMs and eliminates the need for costly human annotations. We first identify salient events by prompting LLMs to generate summaries, from which salient events are identified. Next, we develop an iterative code refinement prompting strategy to generate event relation graphs, removing hallucinated relations and recovering missing edges. Powered by CALLMSAE, we present NYT-SEG, a large-scale automatically annotated event graph dataset which can serve as distant supervision signals. Fine-tuning contextualised graph generation models on NYT-SEG outperforms the models trained on CAEVO data. Results on a human-annotated test set show that the proposed method generates salient and more accurate graphs, outperforming competitive baselines.
%R 10.18653/v1/2025.naacl-long.112
%U https://aclanthology.org/2025.naacl-long.112/
%U https://doi.org/10.18653/v1/2025.naacl-long.112
%P 2223-2245
Markdown (Informal)
[Cascading Large Language Models for Salient Event Graph Generation](https://aclanthology.org/2025.naacl-long.112/) (Tan et al., NAACL 2025)
ACL
- Xingwei Tan, Yuxiang Zhou, Gabriele Pergola, and Yulan He. 2025. Cascading Large Language Models for Salient Event Graph Generation. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 2223–2245, Albuquerque, New Mexico. Association for Computational Linguistics.