@inproceedings{wang-etal-2025-cstree,
    title = "{CST}ree-{SRI}: Introspection-Driven Cognitive Semantic Tree for Multi-Turn Question Answering over Extra-Long Contexts",
    author = "Wang, Zhaowen  and
      Wei, Xiang  and
      Du, Kangshao  and
      Zhang, Yiting  and
      Qin, Libo  and
      Xia, Yingjie  and
      Kuang, Li",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-long.1286/",
    pages = "26502--26525",
    ISBN = "979-8-89176-251-0",
    abstract = "Large Language Models (LLMs) have achieved remarkable success in natural language processing (NLP), particularly in single-turn question answering (QA) on short-text. However, their performance significantly declines when applied to multi-turn QA over extra-long context (ELC), as they struggle to capture the logical correlations across multiple chunks of ELC and maintain the coherence of multi-turn Questions. To address the challenges, we propose the CSTree-SRI framework (Cognitive Semantic Tree through Summarization, Retrieval, and Introspection). CSTree-SRI dynamically constructs the CSTree to preserve logical coherence within ELC through hierarchical synthesis and introspective validation. Then a logic-driven traversal strategy on CSTree is designed to provide efficient information retrieval for question answering. Additionally, we construct a suite of multi-turn QA datasets and an evaluation benchmark tailored for ELC tasks, and comprehensive experiments demonstrate the framework{'}s superiority in addressing the challenges of multi-turn QA over ELC."
}