@inproceedings{wei-etal-2026-lampeae,
title = "{LAMPEAE}: {LLM}-Augmented Manifold Probing for Adaptive Event Argument Extraction",
author = "Wei, Qiyi and
Shang, Wenqian and
Zheng, Bin",
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.105/",
pages = "2478--2494",
ISBN = "979-8-89176-459-0",
abstract = "Event Argument Extraction (EAE) aims to extract arguments for specified events from a text. Previous prompt-based research has mainly focused on designing static role anchors, effectively modeling general semantics but overlooking the geometric rigidity of these representations: (i) they failed to capture the diverse manifold structure of real-world semantic distributions and (ii) they lacked the flexibility to adapt to instance-specific reasoning contexts. To bridge the gap between static parameters and dynamic contexts, we introduce a new framework named LAMPEAE, which reformulates EAE as a dynamic manifold matching problem via adaptive parameter instantiation. Specifically, we employ a neuro-symbolic approach that utilizes a frozen LLM to extract high-order reasoning priors. A lightweight hypernetwork then maps this meta-knowledge into low-rank geometric transformation matrices, which dynamically project original static prompts into instance-specific probes. This mechanism ensures precise semantic alignment within the continuous parameter space. Experimental results on the RAMS, ACE05, and WikiEvent benchmarks show that LAMPEAE establishes new state-of-the-art performance, respectively, effectively validating its superiority in handling heterogeneous semantic transfer."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wei-etal-2026-lampeae">
<titleInfo>
<title>LAMPEAE: LLM-Augmented Manifold Probing for Adaptive Event Argument Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Qiyi</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenqian</namePart>
<namePart type="family">Shang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bin</namePart>
<namePart type="family">Zheng</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>Event Argument Extraction (EAE) aims to extract arguments for specified events from a text. Previous prompt-based research has mainly focused on designing static role anchors, effectively modeling general semantics but overlooking the geometric rigidity of these representations: (i) they failed to capture the diverse manifold structure of real-world semantic distributions and (ii) they lacked the flexibility to adapt to instance-specific reasoning contexts. To bridge the gap between static parameters and dynamic contexts, we introduce a new framework named LAMPEAE, which reformulates EAE as a dynamic manifold matching problem via adaptive parameter instantiation. Specifically, we employ a neuro-symbolic approach that utilizes a frozen LLM to extract high-order reasoning priors. A lightweight hypernetwork then maps this meta-knowledge into low-rank geometric transformation matrices, which dynamically project original static prompts into instance-specific probes. This mechanism ensures precise semantic alignment within the continuous parameter space. Experimental results on the RAMS, ACE05, and WikiEvent benchmarks show that LAMPEAE establishes new state-of-the-art performance, respectively, effectively validating its superiority in handling heterogeneous semantic transfer.</abstract>
<identifier type="citekey">wei-etal-2026-lampeae</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.105/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>2478</start>
<end>2494</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LAMPEAE: LLM-Augmented Manifold Probing for Adaptive Event Argument Extraction
%A Wei, Qiyi
%A Shang, Wenqian
%A Zheng, Bin
%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 wei-etal-2026-lampeae
%X Event Argument Extraction (EAE) aims to extract arguments for specified events from a text. Previous prompt-based research has mainly focused on designing static role anchors, effectively modeling general semantics but overlooking the geometric rigidity of these representations: (i) they failed to capture the diverse manifold structure of real-world semantic distributions and (ii) they lacked the flexibility to adapt to instance-specific reasoning contexts. To bridge the gap between static parameters and dynamic contexts, we introduce a new framework named LAMPEAE, which reformulates EAE as a dynamic manifold matching problem via adaptive parameter instantiation. Specifically, we employ a neuro-symbolic approach that utilizes a frozen LLM to extract high-order reasoning priors. A lightweight hypernetwork then maps this meta-knowledge into low-rank geometric transformation matrices, which dynamically project original static prompts into instance-specific probes. This mechanism ensures precise semantic alignment within the continuous parameter space. Experimental results on the RAMS, ACE05, and WikiEvent benchmarks show that LAMPEAE establishes new state-of-the-art performance, respectively, effectively validating its superiority in handling heterogeneous semantic transfer.
%U https://aclanthology.org/2026.emnlp-main.105/
%P 2478-2494
Markdown (Informal)
[LAMPEAE: LLM-Augmented Manifold Probing for Adaptive Event Argument Extraction](https://aclanthology.org/2026.emnlp-main.105/) (Wei et al., EMNLP 2026)
ACL