Event Extraction in Large Language Model

TL;DR

This paper surveys event extraction in text and multimodal data, emphasizing LLMs, discussing challenges, system components, and future directions for reliable, agent-centric event understanding beyond static extraction.

Contribution

It provides a comprehensive overview of event extraction methods, architectures, and challenges in the LLM era, proposing a system perspective for improved reliability and integration.

Findings

LLMs can generate structured event outputs in zero/few shot settings.

Event schemas and slot constraints aid grounding and verification.

Open challenges include hallucinations, temporal linking, and long horizon knowledge management.

Abstract

Large language models (LLMs) and multimodal LLMs are changing event extraction (EE): prompting and generation can often produce structured outputs in zero shot or few shot settings. Yet LLM based pipelines face deployment gaps, including hallucinations under weak constraints, fragile temporal and causal linking over long contexts and across documents, and limited long horizon knowledge management within a bounded context window. We argue that EE should be viewed as a system component that provides a cognitive scaffold for LLM centered solutions. Event schemas and slot constraints create interfaces for grounding and verification; event centric structures act as controlled intermediate representations for stepwise reasoning; event links support relation aware retrieval with graph based RAG; and event stores offer updatable episodic and agent memory beyond the context window. This survey covers EE in text and multimodal settings, organizing tasks and taxonomy, tracing method evolution from rule based and neural models to instruction driven and generative frameworks, and summarizing formulations, decoding strategies, architectures, representations, datasets, and evaluation. We also review cross lingual, low resource, and domain specific settings, and highlight open challenges and future directions for reliable event centric systems. Finally, we outline open challenges and future directions that are central to the LLM era, aiming to evolve EE from static extraction into a structurally reliable, agent ready perception and memory layer for open world systems.