# Open-Domain Hierarchical Event Schema Induction by Incremental Prompting and Verification

arXiv: https://arxiv.org/abs/2307.01972 · HTML: https://mlsanity.com/paper/2307.01972/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 76 references that are in the map.
- First posted on arXiv 5 Jul 2023.

## Builds on (most cited first, 20 of 20)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [MS MARCO: A Human Generated MAchine Reading COmprehension Dataset](https://mlsanity.com/paper/1611.09268/) (2016)
- [Scaling Language Models: Methods, Analysis & Insights from Training Gopher](https://mlsanity.com/paper/2112.11446/) (2021)
- [ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT](https://mlsanity.com/paper/2004.12832/) (2020)
- [Measuring and Improving Consistency in Pretrained Language Models](https://mlsanity.com/paper/2102.01017/) (2021)
- [Can language models learn from explanations in context?](https://mlsanity.com/paper/2204.02329/) (2022)
- [Rationale-Augmented Ensembles in Language Models](https://mlsanity.com/paper/2207.00747/) (2022)
- [Prompt Consistency for Zero-Shot Task Generalization](https://mlsanity.com/paper/2205.00049/) (2022)
- [Reasoning about Goals, Steps, and Temporal Ordering with WikiHow](https://mlsanity.com/paper/2009.07690/) (2020)
- [Temporal Reasoning on Implicit Events from Distant Supervision](https://mlsanity.com/paper/2010.12753/) (2020)
- [The Future is not One-dimensional: Complex Event Schema Induction by Graph Modeling for Event Prediction](https://mlsanity.com/paper/2104.06344/) (2021)
- [Constructing Narrative Event Evolutionary Graph for Script Event Prediction](https://mlsanity.com/paper/1805.05081/) (2018)
- [Show Me More Details: Discovering Hierarchies of Procedures from Semi-structured Web Data](https://mlsanity.com/paper/2203.07264/) (2022)
- [What do Large Language Models Learn about Scripts?](https://mlsanity.com/paper/2112.13834/) (2021)
- [Event Representations with Tensor-based Compositions](https://mlsanity.com/paper/1711.07611/) (2017)
- [Zero-Shot On-the-Fly Event Schema Induction](https://mlsanity.com/paper/2210.06254/) (2022)
- [Personalized Entity Resolution with Dynamic Heterogeneous Knowledge Graph Representations](https://mlsanity.com/paper/2104.02667/) (2021)

## Built on by (most cited first, 19 of 19)

- [Factuality Challenges in the Era of Large Language Models](https://mlsanity.com/paper/2310.05189/) (2023)
- [Eliminating Position Bias of Language Models: A Mechanistic Approach](https://mlsanity.com/paper/2407.01100/) (2024)
- [Aligning LLMs with Individual Preferences via Interaction](https://mlsanity.com/paper/2410.03642/) (2024)
- [SHIELD: LLM-Driven Schema Induction for Predictive Analytics in EV Battery Supply Chain Disruptions](https://mlsanity.com/paper/2408.05357/) (2024)
- [Grasping the Essentials: Tailoring Large Language Models for Zero-Shot Relation Extraction](https://mlsanity.com/paper/2402.11142/) (2024)
- [Enabling Language Models to Implicitly Learn Self-Improvement](https://mlsanity.com/paper/2310.00898/) (2023)
- [What Makes a Good Natural Language Prompt?](https://mlsanity.com/paper/2506.06950/) (2025)
- [Will LLMs Replace the Encoder-Only Models in Temporal Relation Classification?](https://mlsanity.com/paper/2410.10476/) (2024)
- [LOGOS: LLM-driven End-to-End Grounded Theory Development and Schema Induction for Qualitative Research](https://mlsanity.com/paper/2509.24294/) (2025)
- [Defining a New NLP Playground](https://mlsanity.com/paper/2310.20633/) (2023)
- [Towards Proactive Personalization through Profile Customization for Individual Users in Dialogues](https://mlsanity.com/paper/2512.15302/) (2025)
- [Schema-Guided Culture-Aware Complex Event Simulation with Multi-Agent Role-Play](https://mlsanity.com/paper/2410.18935/) (2024)
- [Lost in Recursion: Mining Rich Event Semantics in Knowledge Graphs](https://mlsanity.com/paper/2404.16405/) (2024)
- [What's on My Network? Using Large Language Models to Identify Real-World IoT Devices at Scale](https://mlsanity.com/paper/2510.13817/) (2025)
- [Distilling Event Sequence Knowledge From Large Language Models](https://mlsanity.com/paper/2401.07237/) (2024)
- [SCI 3.0: A Web-based Schema Curation Interface for Graphical Event Representations](https://mlsanity.com/paper/2405.09733/) (2024)
- [Bridging Human Interpretation and Machine Representation: A Landscape of Qualitative Data Analysis in the LLM Era](https://mlsanity.com/paper/2601.11739/) (2026)
- [Abstract Event Causal Rules: Induction and Application](https://mlsanity.com/paper/2608.05205/) (2026)
- [AutoViewMem: Self-Configuring Orthogonal Views for Conversational Long-Term Memory](https://mlsanity.com/paper/2609.21940/) (2026)

## Abstract (arXiv)

Event schemas are a form of world knowledge about the typical progression of events. Recent methods for event schema induction use information extraction systems to construct a large number of event graph instances from documents, and then learn to generalize the schema from such instances. In contrast, we propose to treat event schemas as a form of commonsense knowledge that can be derived from large language models (LLMs). This new paradigm greatly simplifies the schema induction process and allows us to handle both hierarchical relations and temporal relations between events in a straightforward way. Since event schemas have complex graph structures, we design an incremental prompting and verification method to break down the construction of a complex event graph into three stages: event skeleton construction, event expansion, and event-event relation verification. Compared to directly using LLMs to generate a linearized graph, our method can generate large and complex schemas with 7.2% F1 improvement in temporal relations and 31.0% F1 improvement in hierarchical relations. In addition, compared to the previous state-of-the-art closed-domain schema induction model, human assessors were able to cover ~10% more events when translating the schemas into coherent stories and rated our schemas 1.3 points higher (on a 5-point scale) in terms of readability.