Resources for Brewing BEIR: Reproducible Reference Models and an Official Leaderboard · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2306.07471/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTResources for Brewing BEIR: Reproducible Reference Models and an Official Leaderboard — mentioned by dmezzettihttps://news.ycombinator.com/item?id=37391901urn:hackerpapers:mention:2306.07471:37391901Tue, 05 Sep 2023 14:13:11 GMT<p>It would be good to have a BM25 baseline entry on this leaderboard: https://huggingface.co/spaces/mteb/leaderboard And I&#x27;m sure you&#x27;re aware of the BEIR paper: https://arxiv.org/abs/2306.07471. Elastic references that in this blogpost: https://www.elastic.co/blog/improving-information-retrieval-... I agree that BM25 retrieval + vector re-ranking can work. But vector search does bring results to the table that vanilla BM25 can&#x27;t, even with a large retrieval window. So I do think there is a place for both with the usual &quot;it depends on your data/requirements&quot; caveat.</p><p><a href="https://hackerpaper.kaipfister.de/p/2306.07471/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.IR