Learning to Generate and Extract: A Multi-Agent Collaboration Framework For Zero-shot Document-level Event Arguments Extraction

• URL: http://arxiv.org/abs/2603.02909v2
• Date: Wed, 04 Mar 2026 04:44:45 GMT
• Title: Learning to Generate and Extract: A Multi-Agent Collaboration Framework For Zero-shot Document-level Event Arguments Extraction
• Authors: Guangjun Zhang, Hu Zhang, Yazhou Han, Yue Fan, Yuhang Shao, Ru Li, Hongye Tan,
• Abstract summary: Document-level event argument extraction (DEAE) is essential for knowledge acquisition, aiming to extract participants of events from documents.<n>We introduce a multi-agent collaboration framework for zero-shot document-level event argument extraction (ZS-DEAE)<n>The framework simulates the human collaborative cognitive process of "Propose-Evaluate-Revise"
• Score: 17.868674863387028
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Document-level event argument extraction (DEAE) is essential for knowledge acquisition, aiming to extract participants of events from documents . In the zero-shot setting, existing methods employ LLMs to generate synthetic data to address the challenge posed by the scarcity of annotated data. However, relying solely on Event-type-only prompts makes it difficult for the generated content to accurately capture the contextual and structural relationships of unseen events. Moreover, ensuring the reliability and usability of synthetic data remains a significant challenge due to the absence of quality evaluation mechanisms. To this end, we introduce a multi-agent collaboration framework for zero-shot document-level event argument extraction (ZS-DEAE), which simulates the human collaborative cognitive process of "Propose-Evaluate-Revise." Specifically, the framework comprises a generation agent and an evaluation agent. The generation agent synthesizes data for unseen events by leveraging knowledge from seen events, while the evaluation agent extracts arguments from the synthetic data and assesses their semantic consistency with the context. The evaluation results are subsequently converted into reward signals, with event structure constraints incorporated into the reward design to enable iterative optimization of both agents via reinforcement learning.In three zero-shot scenarios constructed from the RAMS and WikiEvents datasets, our method achieves improvements both in data generation quality and argument extraction performance, while the generated data also effectively enhances the zero-shot performance of other DEAE models.

Related papers

• DeepSynth-Eval: Objectively Evaluating Information Consolidation in Deep Survey Writing [53.85037373860246]
  We introduce Deep Synth-Eval, a benchmark designed to objectively evaluate information consolidation capabilities.<n>We propose a fine-grained evaluation protocol using General Checklists (for factual coverage) and Constraint Checklists (for structural organization)<n>Our results demonstrate that agentic plan-and-write significantly outperform single-turn generation.
  arXiv  Detail & Related papers  (2026-01-07T03:07:52Z)
• Agent4FaceForgery: Multi-Agent LLM Framework for Realistic Face Forgery Detection [108.5042835056188]
  This work introduces Agent4FaceForgery to address two fundamental problems.<n>How to capture the diverse intents and iterative processes of human forgery creation.<n>How to model the complex, often adversarial, text-image interactions that accompany forgeries in social media.
  arXiv  Detail & Related papers  (2025-09-16T01:05:01Z)
• Reflective Agreement: Combining Self-Mixture of Agents with a Sequence Tagger for Robust Event Extraction [9.746352647419345]
  Event Extraction involves automatically identifying and extracting structured information about events from unstructured text.<n>We propose a hybrid approach combining a Self Mixture of Agents with a discriminative sequence tagger.<n>Experiments demonstrate our approach outperforms existing state-of-the-art event extraction methods across three benchmark datasets.
  arXiv  Detail & Related papers  (2025-08-26T18:36:23Z)
• Enhancing Retrieval-Augmented LMs with a Two-stage Consistency Learning Compressor [4.35807211471107]
  This work proposes a novel two-stage consistency learning approach for retrieved information compression in retrieval-augmented language models. The proposed method is empirically validated across multiple datasets, demonstrating notable enhancements in precision and efficiency for question-answering tasks.
  arXiv  Detail & Related papers  (2024-06-04T12:43:23Z)
• Decompose, Enrich, and Extract! Schema-aware Event Extraction using LLMs [45.83950260830323]
  This work focuses on harnessing Large Language Models for automated Event Extraction. It introduces a new method to address hallucination by decomposing the task into Event Detection and Event Argument Extraction.
  arXiv  Detail & Related papers  (2024-06-03T06:55:10Z)
• Consistency Guided Knowledge Retrieval and Denoising in LLMs for Zero-shot Document-level Relation Triplet Extraction [43.50683283748675]
  Document-level Relation Triplet Extraction (DocRTE) is a fundamental task in information systems that aims to simultaneously extract entities with semantic relations from a document. Existing methods heavily rely on a substantial amount of fully labeled data. Recent advanced Large Language Models (LLMs), such as ChatGPT and LLaMA, exhibit impressive long-text generation capabilities.
  arXiv  Detail & Related papers  (2024-01-24T17:04:28Z)
• AMRFact: Enhancing Summarization Factuality Evaluation with AMR-Driven Negative Samples Generation [57.8363998797433]
  We propose AMRFact, a framework that generates perturbed summaries using Abstract Meaning Representations (AMRs) Our approach parses factually consistent summaries into AMR graphs and injects controlled factual inconsistencies to create negative examples, allowing for coherent factually inconsistent summaries to be generated with high error-type coverage.
  arXiv  Detail & Related papers  (2023-11-16T02:56:29Z)
• STAR: Boosting Low-Resource Information Extraction by Structure-to-Text Data Generation with Large Language Models [56.27786433792638]
  STAR is a data generation method that leverages Large Language Models (LLMs) to synthesize data instances. We design fine-grained step-by-step instructions to obtain the initial data instances. Our experiments show that the data generated by STAR significantly improve the performance of low-resource event extraction and relation extraction tasks.
  arXiv  Detail & Related papers  (2023-05-24T12:15:19Z)
• Boosting Event Extraction with Denoised Structure-to-Text Augmentation [52.21703002404442]
  Event extraction aims to recognize pre-defined event triggers and arguments from texts. Recent data augmentation methods often neglect the problem of grammatical incorrectness. We propose a denoised structure-to-text augmentation framework for event extraction DAEE.
  arXiv  Detail & Related papers  (2023-05-16T16:52:07Z)
• SAIS: Supervising and Augmenting Intermediate Steps for Document-Level Relation Extraction [51.27558374091491]
  We propose to explicitly teach the model to capture relevant contexts and entity types by supervising and augmenting intermediate steps (SAIS) for relation extraction. Based on a broad spectrum of carefully designed tasks, our proposed SAIS method not only extracts relations of better quality due to more effective supervision, but also retrieves the corresponding supporting evidence more accurately.
  arXiv  Detail & Related papers  (2021-09-24T17:37:35Z)
• Cross-Supervised Joint-Event-Extraction with Heterogeneous Information Networks [61.950353376870154]
  Joint-event-extraction is a sequence-to-sequence labeling task with a tag set composed of tags of triggers and entities. We propose a Cross-Supervised Mechanism (CSM) to alternately supervise the extraction of triggers or entities. Our approach outperforms the state-of-the-art methods in both entity and trigger extraction.
  arXiv  Detail & Related papers  (2020-10-13T11:51:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.