# Human-in-the-Loop Schema Induction

arXiv: https://arxiv.org/abs/2302.13048 · HTML: https://mlsanity.com/paper/2302.13048/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 34 references that are in the map.
- First posted on arXiv 25 Feb 2023.

## Builds on (most cited first, 12 of 12)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [What Makes Good In-Context Examples for GPT-3?](https://mlsanity.com/paper/2101.06804/) (2021)
- [Simple BERT Models for Relation Extraction and Semantic Role Labeling](https://mlsanity.com/paper/1904.05255/) (2019)
- [Higher-order Coreference Resolution with Coarse-to-fine Inference](https://mlsanity.com/paper/1804.05392/) (2018)
- [Event2Mind: Commonsense Inference on Events, Intents, and Reactions](https://mlsanity.com/paper/1805.06939/) (2018)
- [The Future is not One-dimensional: Complex Event Schema Induction by Graph Modeling for Event Prediction](https://mlsanity.com/paper/2104.06344/) (2021)
- [Zero-Shot On-the-Fly Event Schema Induction](https://mlsanity.com/paper/2210.06254/) (2022)
- [Two Discourse Driven Language Models for Semantics](https://mlsanity.com/paper/1606.05679/) (2016)
- [Machine-Assisted Script Curation](https://mlsanity.com/paper/2101.05400/) (2021)

## Built on by (most cited first, 13 of 13)

- [Language Models Can Improve Event Prediction by Few-Shot Abductive Reasoning](https://mlsanity.com/paper/2305.16646/) (2023)
- [NarraBench: A Comprehensive Framework for Narrative Benchmarking](https://mlsanity.com/paper/2510.09869/) (2025)
- [SHIELD: LLM-Driven Schema Induction for Predictive Analytics in EV Battery Supply Chain Disruptions](https://mlsanity.com/paper/2408.05357/) (2024)
- [OpenPI2.0: An Improved Dataset for Entity Tracking in Texts](https://mlsanity.com/paper/2305.14603/) (2023)
- [Drafting Event Schemas using Language Models](https://mlsanity.com/paper/2305.14847/) (2023)
- [How to Enable Effective Cooperation Between Humans and NLP Models: A Survey of Principles, Formalizations, and Beyond](https://mlsanity.com/paper/2501.05714/) (2025)
- [Choice-75: A Dataset on Decision Branching in Script Learning](https://mlsanity.com/paper/2309.11737/) (2023)
- [Large Language Models to the Rescue: Reducing the Complexity in Scientific Workflow Development Using ChatGPT](https://mlsanity.com/paper/2311.01825/) (2023)
- [HugAgent: A Human Simulation Benchmark for Individual-Level Reasoning](https://mlsanity.com/paper/2510.15144/) (2025)
- [RESIN-EDITOR: A Schema-guided Hierarchical Event Graph Visualizer and Editor](https://mlsanity.com/paper/2312.03093/) (2023)
- [MEEL: Multi-Modal Event Evolution Learning](https://mlsanity.com/paper/2404.10429/) (2024)
- [InterFeedback: Unveiling Interactive Intelligence of Large Multimodal Models via Human Feedback](https://mlsanity.com/paper/2502.15027/) (2025)
- [DanceHA: A Multi-Agent Framework for Document-Level Aspect-Based Sentiment Analysis](https://mlsanity.com/paper/2603.16546/) (2026)

## Abstract (arXiv)

Schema induction builds a graph representation explaining how events unfold in a scenario. Existing approaches have been based on information retrieval (IR) and information extraction(IE), often with limited human curation. We demonstrate a human-in-the-loop schema induction system powered by GPT-3. We first describe the different modules of our system, including prompting to generate schematic elements, manual edit of those elements, and conversion of those into a schema graph. By qualitatively comparing our system to previous ones, we show that our system not only transfers to new domains more easily than previous approaches, but also reduces efforts of human curation thanks to our interactive interface.