# InteractiveIE: Towards Assessing the Strength of Human-AI Collaboration in Improving the Performance of Information Extraction

arXiv: https://arxiv.org/abs/2305.14659 · HTML: https://mlsanity.com/paper/2305.14659/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 42 references that are in the map.
- First posted on arXiv 24 May 2023.

## Builds on (most cited first, 23 of 23)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Least-to-Most Prompting Enables Complex Reasoning in Large Language Models](https://mlsanity.com/paper/2205.10625/) (2022)
- [Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks](https://mlsanity.com/paper/2211.12588/) (2022)
- [Measuring and Narrowing the Compositionality Gap in Language Models](https://mlsanity.com/paper/2210.03350/) (2022)
- [PAL: Program-aided Language Models](https://mlsanity.com/paper/2211.10435/) (2022)
- [How Close is ChatGPT to Human Experts? Comparison Corpus, Evaluation, and Detection](https://mlsanity.com/paper/2301.07597/) (2023)
- [CUAD: An Expert-Annotated NLP Dataset for Legal Contract Review](https://mlsanity.com/paper/2103.06268/) (2021)
- [PAQ: 65 Million Probably-Asked Questions and What You Can Do With Them](https://mlsanity.com/paper/2102.07033/) (2021)
- [Maieutic Prompting: Logically Consistent Reasoning with Recursive Explanations](https://mlsanity.com/paper/2205.11822/) (2022)
- [ChatGPT or Human? Detect and Explain. Explaining Decisions of Machine Learning Model for Detecting Short ChatGPT-generated Text](https://mlsanity.com/paper/2301.13852/) (2023)
- [Neural Open Information Extraction](https://mlsanity.com/paper/1805.04270/) (2018)
- [SelfORE: Self-supervised Relational Feature Learning for Open Relation Extraction](https://mlsanity.com/paper/2004.02438/) (2020)
- [The Future is not One-dimensional: Complex Event Schema Induction by Graph Modeling for Event Prediction](https://mlsanity.com/paper/2104.06344/) (2021)
- [Reading the Manual: Event Extraction as Definition Comprehension](https://mlsanity.com/paper/1912.01586/) (2019)
- [Bot or Human? Detecting ChatGPT Imposters with A Single Question](https://mlsanity.com/paper/2305.06424/) (2023)
- [Improved Trust in Human-Robot Collaboration with ChatGPT](https://mlsanity.com/paper/2304.12529/) (2023)
- [Revisiting Unsupervised Relation Extraction](https://mlsanity.com/paper/2005.00087/) (2020)
- [Humans are Still Better than ChatGPT: Case of the IEEEXtreme Competition](https://mlsanity.com/paper/2305.06934/) (2023)
- [Slot Filling for Biomedical Information Extraction](https://mlsanity.com/paper/2109.08564/) (2021)
- [PromptORE -- A Novel Approach Towards Fully Unsupervised Relation Extraction](https://mlsanity.com/paper/2304.01209/) (2023)
- [PIE-QG: Paraphrased Information Extraction for Unsupervised Question Generation from Small Corpora](https://mlsanity.com/paper/2301.01064/) (2023)

## Built on by (most cited first, 1 of 1)

- [How the Advent of Ubiquitous Large Language Models both Stymie and Turbocharge Dynamic Adversarial Question Generation](https://mlsanity.com/paper/2401.11185/) (2024)

## Abstract (arXiv)

Learning template based information extraction from documents is a crucial yet difficult task. Prior template-based IE approaches assume foreknowledge of the domain templates; however, real-world IE do not have pre-defined schemas and it is a figure-out-as you go phenomena. To quickly bootstrap templates in a real-world setting, we need to induce template slots from documents with zero or minimal supervision. Since the purpose of question answering intersect with the goal of information extraction, we use automatic question generation to induce template slots from the documents and investigate how a tiny amount of a proxy human-supervision on-the-fly (termed as InteractiveIE) can further boost the performance. Extensive experiments on biomedical and legal documents, where obtaining training data is expensive, reveal encouraging trends of performance improvement using InteractiveIE over AI-only baseline.