@inproceedings{bao-etal-2025-r2a,
    title = "{R}2{A}-{TLS}: Reflective Retrieval-Augmented Timeline Summarization with Causal-Semantic Integration",
    author = "Bao, Chenlong  and
      Li, Shijie  and
      Hu, Minghao  and
      Qiao, Ming  and
      Zhang, Bin  and
      Tang, Jin-Tao  and
      Li, Shasha  and
      Wang, Ting",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.40/",
    doi = "10.18653/v1/2025.findings-emnlp.40",
    pages = "752--766",
    ISBN = "979-8-89176-335-7",
    abstract = "Open-domain timeline summarization (TLS) faces challenges from information overload and data sparsity when processing large-scale textual streams. Existing methods struggle to capture coherent event narratives due to fragmented descriptions and often accumulate noise through iterative retrieval strategies that lack effective relevance evaluation. This paper proposes: Reflective Retrieval-Augmented Timeline Summarization with Causal-Semantic Intergration, which offers a novel perspective for open-domain TLS by time point completion and event element completion. $R2A-TLS$ establishes an initial retrieval, reflection, and deep retrieval system that reduces noise through a double filtering mechanism that iteratively generates a timeline for each text which passes the filtering. Then, the system reflects on the initial timeline with the aim of identifying information gaps through causal chain analysis and FrameNet based element validation. These gaps are reformulated into targeted queries to trigger deep retrieval for refining timeline coherence and density. Empirical evaluation on Open-TLS dataset reveals that our approach outperforms the best prior published approaches."
}