Report on the 18th Round of NII Testbeds and Community for Information Access Research (NTCIR-18)
Bibliographic record
Abstract
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/.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.064 | 0.040 |
| Meta-epidemiology (narrow) | 0.003 | 0.001 |
| Meta-epidemiology (broad) | 0.003 | 0.002 |
| Bibliometrics | 0.005 | 0.003 |
| Science and technology studies | 0.006 | 0.002 |
| Scholarly communication | 0.010 | 0.006 |
| Open science | 0.005 | 0.016 |
| Research integrity | 0.004 | 0.007 |
| Insufficient payload (model declined to judge) | 0.080 | 0.065 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".