CURIE: An Iterative Querying Approach for Reasoning About Situations
This addresses the challenge of eliciting relevant consequences in situational reasoning, particularly for tasks requiring background knowledge and multi-hop reasoning, though it is incremental as it builds on existing language model methods.
The paper tackles the problem of situational reasoning by proposing CURIE, an iterative querying approach that builds structured situational graphs to predict consequences of new situations, improving accuracy on a reasoning end task by 3 points.
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.