English

Analyzing and Mitigating Repetitions in Trip Recommendation

Information Retrieval 2025-07-29 v1 Machine Learning

Abstract

Trip recommendation has emerged as a highly sought-after service over the past decade. Although current studies significantly understand human intention consistency, they struggle with undesired repetitive outcomes that need resolution. We make two pivotal discoveries using statistical analyses and experimental designs: (1) The occurrence of repetitions is intricately linked to the models and decoding strategies. (2) During training and decoding, adding perturbations to logits can reduce repetition. Motivated by these observations, we introduce AR-Trip (Anti Repetition for Trip Recommendation), which incorporates a cycle-aware predictor comprising three mechanisms to avoid duplicate Points-of-Interest (POIs) and demonstrates their effectiveness in alleviating repetition. Experiments on four public datasets illustrate that AR-Trip successfully mitigates repetition issues while enhancing precision.

Keywords

Cite

@article{arxiv.2507.19798,
  title  = {Analyzing and Mitigating Repetitions in Trip Recommendation},
  author = {Wenzheng Shu and Kangqi Xu and Wenxin Tai and Ting Zhong and Yong Wang and Fan Zhou},
  journal= {arXiv preprint arXiv:2507.19798},
  year   = {2025}
}

Comments

Accepted by ACM SIGIR 2024 Short Paper Track

R2 v1 2026-07-01T04:19:52.933Z