Reproduce “Neural Re-ranking in Multi-stage Recommender Systems: A Review” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Weiwen Liu, Yunjia Xi, Jiarui Qin, Fei Sun, Bo Chen, Weinan Zhang, Rui Zhang, Ruiming Tang
The authors review neural re-ranking methods, organizing them by objective—accuracy alone or multiple goals—and whether they learn from displayed feedback or evaluator estimates for unshown orderings. Listwise models use interactions among candidates; the review identifies diversity/fairness and counterfactual multi-objective learning as less explored. On PRM Public, PRM reaches NDCG@20 of 0.4301 versus 0.3202 initially; this offline result is not evidence of user impact.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.