# Improving Event Definition Following For Zero-Shot Event Detection

arXiv: https://arxiv.org/abs/2403.02586 · HTML: https://mlsanity.com/paper/2403.02586/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 57 references that are in the map.
- First posted on arXiv 5 Mar 2024.

## Builds on (most cited first, 30 of 34)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Making Pre-trained Language Models Better Few-shot Learners](https://mlsanity.com/paper/2012.15723/) (2020)
- [Large Language Models are not Fair Evaluators](https://mlsanity.com/paper/2305.17926/) (2023)
- [Entity, Relation, and Event Extraction with Contextualized Span Representations](https://mlsanity.com/paper/1909.03546/) (2019)
- [ChatIE: Zero-Shot Information Extraction via Chatting with ChatGPT](https://mlsanity.com/paper/2302.10205/) (2023)
- [ZeroGen: Efficient Zero-shot Learning via Dataset Generation](https://mlsanity.com/paper/2202.07922/) (2022)
- [Generating Training Data with Language Models: Towards Zero-Shot Language Understanding](https://mlsanity.com/paper/2202.04538/) (2022)
- [Generating Datasets with Pretrained Language Models](https://mlsanity.com/paper/2104.07540/) (2021)
- [Structured Prediction as Translation between Augmented Natural Languages](https://mlsanity.com/paper/2101.05779/) (2021)
- [Event Extraction by Answering (Almost) Natural Questions](https://mlsanity.com/paper/2004.13625/) (2020)
- [Evaluating ChatGPT's Information Extraction Capabilities: An Assessment of Performance, Explainability, Calibration, and Faithfulness](https://mlsanity.com/paper/2304.11633/) (2023)
- [Exploiting Asymmetry for Synthetic Training Data Generation: SynthIE and the Case of Information Extraction](https://mlsanity.com/paper/2303.04132/) (2023)
- [Exploring the Feasibility of ChatGPT for Event Extraction](https://mlsanity.com/paper/2303.03836/) (2023)
- [Code4Struct: Code Generation for Few-Shot Event Structure Prediction](https://mlsanity.com/paper/2210.12810/) (2022)
- [Zero-Shot Transfer Learning for Event Extraction](https://mlsanity.com/paper/1707.01066/) (2017)
- [Cross-media Structured Common Space for Multimedia Event Extraction](https://mlsanity.com/paper/2005.02472/) (2020)
- [RelationPrompt: Leveraging Prompts to Generate Synthetic Data for Zero-Shot Relation Triplet Extraction](https://mlsanity.com/paper/2203.09101/) (2022)
- [Active Instruction Tuning: Improving Cross-Task Generalization by Training on Prompt Sensitive Tasks](https://mlsanity.com/paper/2311.00288/) (2023)
- [Neural Data Augmentation via Example Extrapolation](https://mlsanity.com/paper/2102.01335/) (2021)
- [Do Models Really Learn to Follow Instructions? An Empirical Study of Instruction Tuning](https://mlsanity.com/paper/2305.11383/) (2023)
- [Did You Read the Instructions? Rethinking the Effectiveness of Task Definitions in Instruction Learning](https://mlsanity.com/paper/2306.01150/) (2023)
- [Summarization as Indirect Supervision for Relation Extraction](https://mlsanity.com/paper/2205.09837/) (2022)
- [Unsupervised Label-aware Event Trigger and Argument Classification](https://mlsanity.com/paper/2012.15243/) (2020)
- [GENEVA: Benchmarking Generalizability for Event Argument Extraction with Hundreds of Event Types and Argument Roles](https://mlsanity.com/paper/2205.12505/) (2022)
- [Deep Structured Neural Network for Event Temporal Relation Extraction](https://mlsanity.com/paper/1909.10094/) (2019)
- [Textual Entailment for Event Argument Extraction: Zero- and Few-Shot with Multi-Source Learning](https://mlsanity.com/paper/2205.01376/) (2022)
- [DICE: Data-Efficient Clinical Event Extraction with Generative Models](https://mlsanity.com/paper/2208.07989/) (2022)
- [Document-level Event Extraction with Efficient End-to-end Learning of Cross-event Dependencies](https://mlsanity.com/paper/2010.12787/) (2020)
- [MEE: A Novel Multilingual Event Extraction Dataset](https://mlsanity.com/paper/2211.05955/) (2022)
- [GLEN: General-Purpose Event Detection for Thousands of Types](https://mlsanity.com/paper/2303.09093/) (2023)

## Built on by (most cited first, 7 of 7)

- [Instruction-Tuning LLMs for Event Extraction with Annotation Guidelines](https://mlsanity.com/paper/2502.16377/) (2025)
- [SPEED++: A Multilingual Event Extraction Framework for Epidemic Prediction and Preparedness](https://mlsanity.com/paper/2410.18393/) (2024)
- [Event Extraction in Large Language Model](https://mlsanity.com/paper/2512.19537/) (2025)
- [SNaRe: Domain-aware Data Generation for Low-Resource Event Detection](https://mlsanity.com/paper/2502.17394/) (2025)
- [SEOE: A Scalable and Reliable Semantic Evaluation Framework for Open Domain Event Detection](https://mlsanity.com/paper/2503.03303/) (2025)
- [Extracting Events Like Code: A Multi-Agent Programming Framework for Zero-Shot Event Extraction](https://mlsanity.com/paper/2511.13118/) (2025)
- [EAGER: Enhancing Generative Event Extraction via Reinforcement Learning with Verifiable Rewards](https://mlsanity.com/paper/2609.29230/) (2026)

## Abstract (arXiv)

Existing approaches on zero-shot event detection usually train models on datasets annotated with known event types, and prompt them with unseen event definitions. These approaches yield sporadic successes, yet generally fall short of expectations. In this work, we aim to improve zero-shot event detection by training models to better follow event definitions. We hypothesize that a diverse set of event types and definitions are the key for models to learn to follow event definitions while existing event extraction datasets focus on annotating many high-quality examples for a few event types. To verify our hypothesis, we construct an automatically generated Diverse Event Definition (DivED) dataset and conduct comparative studies. Our experiments reveal that a large number of event types (200) and diverse event definitions can significantly boost event extraction performance; on the other hand, the performance does not scale with over ten examples per event type. Beyond scaling, we incorporate event ontology information and hard-negative samples during training, further boosting the performance. Based on these findings, we fine-tuned a LLaMA-2-7B model on our DivED dataset, yielding performance that surpasses SOTA large language models like GPT-3.5 across three open benchmarks on zero-shot event detection.