# Small Models Are (Still) Effective Cross-Domain Argument Extractors

arXiv: https://arxiv.org/abs/2404.08579 · HTML: https://mlsanity.com/paper/2404.08579/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 27 references that are in the map.
- First posted on arXiv 12 Apr 2024.

## Builds on (most cited first, 9 of 9)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [Event Extraction by Answering (Almost) Natural Questions](https://mlsanity.com/paper/2004.13625/) (2020)
- [Document-Level Event Argument Extraction by Conditional Generation](https://mlsanity.com/paper/2104.05919/) (2021)
- [Prompt for Extraction? PAIE: Prompting Argument Interaction for Event Argument Extraction](https://mlsanity.com/paper/2202.12109/) (2022)
- [Document-level Entity-based Extraction as Template Generation](https://mlsanity.com/paper/2109.04901/) (2021)
- [Reading the Manual: Event Extraction as Definition Comprehension](https://mlsanity.com/paper/1912.01586/) (2019)
- [A Unified View of Evaluation Metrics for Structured Prediction](https://mlsanity.com/paper/2310.13793/) (2023)
- [Asking the Right Questions in Low Resource Template Extraction](https://mlsanity.com/paper/2205.12643/) (2022)

## Abstract (arXiv)

Effective ontology transfer has been a major goal of recent work on event argument extraction (EAE). Two methods in particular -- question answering (QA) and template infilling (TI) -- have emerged as promising approaches to this problem. However, detailed explorations of these techniques' ability to actually enable this transfer are lacking. In this work, we provide such a study, exploring zero-shot transfer using both techniques on six major EAE datasets at both the sentence and document levels. Further, we challenge the growing reliance on LLMs for zero-shot extraction, showing that vastly smaller models trained on an appropriate source ontology can yield zero-shot performance superior to that of GPT-3.5 or GPT-4.