Document Type

Conference Proceeding

Subject Area(s)

LLMs, question answering, AI


Large Language Models have excelled at encoding and leveraging language patterns in large text-based corpora for various tasks, including spatiotemporal event-based question answering (QA). However, due to encoding a text-based projection of the world, they have also been shown to lack a fullbodied understanding of such events, e.g., a sense of intuitive physics, and cause-and-effect relationships among events. In this work, we propose using causal event graphs (CEGs) to enhance language understanding of spatiotemporal events in language models, using a novel approach that also provides proofs for the model’s capture of the CEGs. A CEG consists of events denoted by nodes, and edges that denote causeand- effect relationships among the events. We perform experimentation and evaluation of our approach for benchmark spatiotemporal QA tasks and show effective performance, both quantitative and qualitative, over state-of-the-art baseline methods1.

APA Citation

Roy, K., Oltramari, A., Zi, Y., Shyalika, C., Narayanan, V., & Sheth, A. (2024). Causal event graph-guided language-based spatiotemporal question answering. [Preprint]