CURIE: An Iterative Querying Approach for Reasoning About Situations
Abstract
Recently, models have been shown to predict the effects of unexpected situations, e.g., would cloudy skies help or hinder plant growth? Given a context, the goal of such situational reasoning is to elicit the consequences of a new situation (st) that arises in that context. We propose a method to iteratively build a graph of relevant consequences explicitly in a structured situational graph (st-graph) using natural language queries over a finetuned language model (M). Across multiple domains, CURIE generates st-graphs that humans find relevant and meaningful in eliciting the consequences of a new situation. We show that st-graphs generated by CURIE improve a situational reasoning end task (WIQA-QA) by 3 points on accuracy by simply augmenting their input with our generated situational graphs, especially for a hard subset that requires background knowledge and multi-hop reasoning.
Keywords
Cite
@article{arxiv.2104.00814,
title = {CURIE: An Iterative Querying Approach for Reasoning About Situations},
author = {Dheeraj Rajagopal and Aman Madaan and Niket Tandon and Yiming Yang and Shrimai Prabhumoye and Abhilasha Ravichander and Peter Clark and Eduard Hovy},
journal= {arXiv preprint arXiv:2104.00814},
year = {2021}
}
Comments
This paper builds upon EIGEN (arXiv:2010.11764) and proposes a general framework for situational reasoning