Papers by Tetsuhisa Suizu

1 papers
Automatic Generation of a Compositional QA Benchmark for Geospatial Reasoning under Spatial and Entity Constraints (2026.eacl-srw)

Copied to clipboard

Challenge: Recent advances in large language models have enhanced their ability to perform reasoning tasks that integrate linguistic, visual, and factual information.
Approach: They propose a method for constructing compositional geographic question answering datasets that jointly consider spatial and entity constraints.
Outcome: The proposed method performs well on questions involving rich entity grounding, but its accuracy drops on quantitative spatial reasoning questions.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations