Metraipolis › archive › dc_db509355b791
Do Sequential Recommendation Benchmarks Really Require Higher-Order Sequence Modelling? — arXiv:2608.19833
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.19833
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T12:03:29.378Z
- SHA-256 of the archived text
12a782e4375c045a4498208568aa8899d34e778945a387d37be8cb3cac9e2155- Stable URL of this page
https://metraipolis.com/documento/dc_db509355b791
How to cite
Do Sequential Recommendation Benchmarks Really Require Higher-Order Sequence Modelling? — arXiv:2608.19833 — arXiv (en), https://arxiv.org/abs/2608.19833 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_db509355b791 (Metraipolis archive dc_db509355b791, sha256 12a782e4375c045a4498208568aa8899d34e778945a387d37be8cb3cac9e2155)
BibTeX
@misc{dcdb509355b791,
title = {Do Sequential Recommendation Benchmarks Really Require Higher-Order Sequence Modelling? — arXiv:2608.19833},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.19833},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_db509355b791; sha256 12a782e4375c045a4498208568aa8899d34e778945a387d37be8cb3cac9e2155},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.19833. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Sequential recommenders increasingly use language-model architectures designed to capture complex, context-dependent interactions. Yet it remains unclear whether widely used benchmarks actually require this modelling capacity. We investigate this question using two simple, recency-weighted pairwise probes that do not learn higher-order sequence representations: Sequential Rules (SeqRules) and our Probabilistic Collaborative Transition Model (PCTM). Using the evaluation protocol of eSASRec, at least one probe exceeds our eSASRec reproduction by 15-38% on three Amazon datasets and by 4.4% on MovieLens-1M, but trails it by 27.3% on MovieLens-20M. On the four remaining datasets, at least one probe also outperforms our sampled-softmax SASRec reproduction by 9-28%, suggesting that these widely used benchmarks are poorly suited to measuring gains from higher-order sequence modelling. More broadly, comparing Transformer-based models against strong recency-weighted pairwise probes provides a concrete test of whether a benchmark can meaningfully measure gains from higher-order sequence modelling. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-21 in cs.IR). Categorie arXiv: Information Retrieval (cs.IR). Pagina del lavoro: https://arxiv.org/abs/2608.19833 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-18T12:01:23.930Z dalla pagina https://arxiv.org/catchup/cs.IR/2026-08-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).