uema2lab_rrf_k10 — Retrieval Only Task

Is this a manual (human intervention) or automatic run?: automatic
Does this run leverage neural networks?: yes
Does this run leverage proprietary models in any step of the retrieval pipeline?: yes
Does this run leverage open-weight LLMs (> 5B parameters) in any step of the retrieval pipeline?: no
Does this run leverage smaller open-weight language models in any step of the retrieval pipeline?: no
Was this run padded with results from a baseline run?: N/A
What would you categorize this run as?: Ensemble/Fusion of First Stages
Please provide a short description of this run: In this system, each narrative query was first decomposed into multiple sub-queries. For each sub-query, both sparse (BM25) and dense (vector-based) retrieval were performed on a document-level index, and the top 100 documents were retrieved. These ranked lists for each sub-query were then merged using Reciprocal Rank Fusion (RRF) with rrf_K=10 to produce a final ranked list of documents at the narrative-query level. Each document in the ranked list was segmented into smaller textual segments, and each segment was considered a candidate. We computed embedding-based similarity between each segment and the original narrative query, and selected the most relevant segment for each document. This final ranked list of segments was submitted as the run.
Please give this run a priority for inclusion in manual assessments.: 1 (top)