# EIGEN: Event Influence GENeration using Pre-trained Language Models

arXiv: https://arxiv.org/abs/2010.11764 · HTML: https://mlsanity.com/paper/2010.11764/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Oct 2020.

## Built on by (most cited first, 8 of 8)

- [Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey](https://mlsanity.com/paper/2111.01243/) (2021)
- [ExplaGraphs: An Explanation Graph Generation Task for Structured Commonsense Reasoning](https://mlsanity.com/paper/2104.07644/) (2021)
- [DAGN: Discourse-Aware Graph Network for Logical Reasoning](https://mlsanity.com/paper/2103.14349/) (2021)
- [Explanation Graph Generation via Pre-trained Language Models: An Empirical Study with Contrastive Learning](https://mlsanity.com/paper/2204.04813/) (2022)
- [Relational Gating for "What If" Reasoning](https://mlsanity.com/paper/2105.13449/) (2021)
- [Relevant CommonSense Subgraphs for "What if..." Procedural Reasoning](https://mlsanity.com/paper/2203.11187/) (2022)
- [Discourse-Aware Graph Networks for Textual Logical Reasoning](https://mlsanity.com/paper/2207.01450/) (2022)
- [Explanation Graph Generation via Generative Pre-training over Synthetic Graphs](https://mlsanity.com/paper/2306.00652/) (2023)

## Abstract (arXiv)

Reasoning about events and tracking their influences is fundamental to understanding processes. In this paper, we present EIGEN - a method to leverage pre-trained language models to generate event influences conditioned on a context, nature of their influence, and the distance in a reasoning chain. We also derive a new dataset for research and evaluation of methods for event influence generation. EIGEN outperforms strong baselines both in terms of automated evaluation metrics (by 10 ROUGE points) and human judgments on closeness to reference and relevance of generations. Furthermore, we show that the event influences generated by EIGEN improve the performance on a "what-if" Question Answering (WIQA) benchmark (over 3% F1), especially for questions that require background knowledge and multi-hop reasoning.