This event report summarizes the eighteenth round of the NII Testbeds and Community for Information Access Research (NTCIR-18), held on June 10–13, 2025 in Tokyo, Japan. NTCIR-18 organized seven core tasks (AEOLLM, FairWeb-2, FinArg-2, Lifelog-6, MedNLP-CHAT, RadNLP, Transfer-2) and three pilot tasks (HIDDEN-RAD, SUSHI, U4), spanning evaluation of generative LLMs, fair ranking, temporal reasoning in finance, multimodal lifelog retrieval, safety assessment for medical dialogue, bilingual radiology staging, resource transfer for dense retrieval, causal explanation in radiology, search over archival metadata, and table-centric QA over annual reports. Across 178 registrations from 113 teams worldwide, participants submitted runs and analyses that combined traditional IR pipelines with LLM-centric methods. This report outlines each task's motivation, data, and methodology, and summarize key findings, including the complementary roles of LLM-based and feature-based evaluators, trade-offs and mitigations in fairness-aware ranking, the importance of structure-aware approaches for tables, and the persistent challenges of sparse metadata and clinical reasoning. Date: 10–13 June 2025. Website: https://research.nii.ac.jp/ntcir/ntcir-18/.
Chen et al. (Mon,) studied this question.