@inproceedings{kim-kim-2022-saving,
    title = "Saving Dense Retriever from Shortcut Dependency in Conversational Search",
    author = "Kim, Sungdong  and
      Kim, Gangwoo",
    editor = "Goldberg, Yoav  and
      Kozareva, Zornitsa  and
      Zhang, Yue",
    booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
    month = dec,
    year = "2022",
    address = "Abu Dhabi, United Arab Emirates",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2022.emnlp-main.701/",
    doi = "10.18653/v1/2022.emnlp-main.701",
    pages = "10278--10287",
    abstract = "Conversational search (CS) needs a holistic understanding of conversational inputs to retrieve relevant passages. In this paper, we demonstrate the existence of a \textit{retrieval shortcut} in CS, which causes models to retrieve passages solely relying on partial history while disregarding the latest question. With in-depth analysis, we first show that naively trained dense retrievers heavily exploit the shortcut and hence perform poorly when asked to answer history-independent questions. To build more robust models against shortcut dependency, we explore various hard negative mining strategies. Experimental results show that training with the model-based hard negatives effectively mitigates the dependency on the shortcut, significantly improving dense retrievers on recent CS benchmarks. In particular, our retriever outperforms the previous state-of-the-art model by 11.0 in Recall@10 on QReCC."
}