AAAI 2026technical0 citations

Assessing LLMs for Serendipity Discovery in Knowledge Graphs: A Case for Drug Repurposing

Mengying Wang, Chenhui Ma, Ao Jiao, Tuo Liang, Pengjun Lu, Shrinidhi Hegde, Yu Yin, Evren Gurkan-Cavusoglu

Abstract

Large Language Models (LLMs) have greatly advanced knowledge graph question answering (KGQA), yet existing systems are typically optimized for returning highly relevant but predictable answers. A missing yet desired capacity is to exploit LLMs to suggest surprise and novel ("serendipitious") answers. In this paper, we formally define the serendipity-aware KGQA task and propose the SerenQA framework to evaluate LLMs

BibTeX
@inproceedings{aaai2026_assessingllmsfor,
  title = {Assessing LLMs for Serendipity Discovery in Knowledge Graphs: A Case for Drug Repurposing},
  author = {Mengying Wang and Chenhui Ma and Ao Jiao and Tuo Liang and Pengjun Lu and Shrinidhi Hegde and Yu Yin and Evren Gurkan-Cavusoglu and Yinghui Wu},
  booktitle = {AAAI 2026},
  year = {2026}
}