# What-if I ask you to explain: Explaining the effects of perturbations in procedural text

arXiv: https://arxiv.org/abs/2005.01526 · HTML: https://mlsanity.com/paper/2005.01526/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 May 2020.

## Built on by (most cited first, 9 of 9)

- [DAGN: Discourse-Aware Graph Network for Logical Reasoning](https://mlsanity.com/paper/2103.14349/) (2021)
- [Causal Reasoning of Entities and Events in Procedural Texts](https://mlsanity.com/paper/2301.10896/) (2023)
- [Show Me More Details: Discovering Hierarchies of Procedures from Semi-structured Web Data](https://mlsanity.com/paper/2203.07264/) (2022)
- [Reasoning about Procedures with Natural Language Processing: A Tutorial](https://mlsanity.com/paper/2205.07455/) (2022)
- [OpenPI2.0: An Improved Dataset for Entity Tracking in Texts](https://mlsanity.com/paper/2305.14603/) (2023)
- [Relational Gating for "What If" Reasoning](https://mlsanity.com/paper/2105.13449/) (2021)
- [CURIE: An Iterative Querying Approach for Reasoning About Situations](https://mlsanity.com/paper/2104.00814/) (2021)
- [Relevant CommonSense Subgraphs for "What if..." Procedural Reasoning](https://mlsanity.com/paper/2203.11187/) (2022)
- [Towards Human-Centred Explainability Benchmarks For Text Classification](https://mlsanity.com/paper/2211.05452/) (2022)

## Abstract (arXiv)

We address the task of explaining the effects of perturbations in procedural text, an important test of process comprehension. Consider a passage describing a rabbit's life-cycle: humans can easily explain the effect on the rabbit population if a female rabbit becomes ill -- i.e., the female rabbit would not become pregnant, and as a result not have babies leading to a decrease in rabbit population. We present QUARTET, a system that constructs such explanations from paragraphs, by modeling the explanation task as a multitask learning problem. QUARTET provides better explanations (based on the sentences in the procedural text) compared to several strong baselines on a recent process comprehension benchmark. We also present a surprising secondary effect: our model also achieves a new SOTA with a 7% absolute F1 improvement on a downstream QA task. This illustrates that good explanations do not have to come at the expense of end task performance.