We are excited to share two LARK Lab papers accepted to EMNLP 2026 in Budapest, Hungary! This year, our work at EMNLP shares a common theme: What’s under the hood of large language models?

We are excited to share that our paper LogosKG: Hardware-Optimized Scalable and Interpretable Knowledge Graph Retrieval has been accepted to the main conference at ACL 2026. This work is led by He Cheng, PhD, postdoc researcher in our lab.

We’re thrilled to share that two of our papers were accepted and presented at EMNLP 2025, held this year in Suzhou, China: one in the Main Conference and one in the Findings of EMNLP.

We are delighted to announce that our paper, “Brittleness and Promise: Knowledge Graph Based Reward Modeling for Diagnostic Reasoning,” has been accepted to the GenAI4Health workshop at NeurIPS 2025! In this paper, we explore a new paradigm for incorporating knowledge graphs (KGs) by framing our problem as reward modeling over KG paths.

We are excited to announce that our paper, “Efficient and Scalable Retrieval in Knowledge Graphs: From Single-Graph to Partitioned Multi-Graph Approaches,” has been accepted to the AMIA 2025 NLP Annual Symposium!