@inproceedings{kim-etal-2025-connecting,
    title = "Connecting the Knowledge Dots: Retrieval-augmented Knowledge Connection for Commonsense Reasoning",
    author = "Kim, Junho  and
      Bak, Soyeon  and
      Lee, Mingyu  and
      Hong, Minju  and
      Kim, Songha  and
      Kam, Tae-Eui  and
      Lee, SangKeun",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.1203/",
    pages = "23582--23601",
    ISBN = "979-8-89176-332-6",
    abstract = "While large language models (LLMs) have achieved remarkable performance across various natural language processing (NLP) tasks, LLMs exhibit a limited understanding of commonsense reasoning due to the necessity of implicit knowledge that is rarely expressed in text. Recently, retrieval-augmented language models (RALMs) have enhanced their commonsense reasoning ability by incorporating background knowledge from external corpora. However, previous RALMs overlook the implicit nature of commonsense knowledge, potentially resulting in the retrieved documents not directly containing information needed to answer questions. In this paper, we propose Retrieval-augmented knowledge Connection, ReConnect, which transforms indirectly relevant documents into a direct explanation to answer the given question. To this end, we extract relevant knowledge from various retrieved document subsets and aggregate them into a direct explanation. Experimental results show that ReConnect outperforms state-of-the-art (SOTA) baselines, achieving improvements of +2.0{\%} and +4.6{\%} average accuracy on in-domain (ID) and out-of-domain (OOD) benchmarks, respectively."
}