@inproceedings{schumacher-etal-2025-raster,
    title = "{RAST}e{R}: Robust, Agentic, and Structured Temporal Reasoning",
    author = "Schumacher, Dan  and
      Haji, Fatemeh  and
      Grey, Tara  and
      Bandlamudi, Niharika  and
      Karnik, Nupoor  and
      Kumar, Gagana Uday  and
      Chiang, Cho-Yu Jason  and
      Najafirad, Peyman  and
      Vishwamitra, Nishant  and
      Rios, Anthony",
    editor = "Inui, Kentaro  and
      Sakti, Sakriani  and
      Wang, Haofen  and
      Wong, Derek F.  and
      Bhattacharyya, Pushpak  and
      Banerjee, Biplab  and
      Ekbal, Asif  and
      Chakraborty, Tanmoy  and
      Singh, Dhirendra Pratap",
    booktitle = "Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics",
    month = dec,
    year = "2025",
    address = "Mumbai, India",
    publisher = "The Asian Federation of Natural Language Processing and The Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-ijcnlp-aacl/2025.ijcnlp-long.166/",
    pages = "3098--3123",
    ISBN = "979-8-89176-298-5",
    abstract = "Temporal question answering (TQA) remains a persistent challenge for large language models (LLMs), particularly in retrieval-augmented generation (RAG) settings where retrieved content may be irrelevant, outdated, or temporally inconsistent. This is especially critical in applications like clinical event ordering, policy tracking, and real-time decision-making, which require reliable temporal reasoning even under noisy or misleading context. To address this challenge, we introduce RASTeR: Robust, Agentic, and Structured, Temporal Reasoning, an agentic prompting framework that separates context evaluation from answer generation. RASTeR first assesses the relevance and temporal coherence of retrieved context, then constructs a structured temporal knowledge graph (TKG) to better facilitate reasoning. When inconsistencies are detected, RASTeR selectively corrects or discards context before generating an answer. Across multiple datasets and LLMs, RASTeR consistently improves robustness: defined here as the model{'}s ability to generate correct predictions despite suboptimal context. We further validate our approach through a ``needle-in-the-haystack'' study, in which relevant context is buried among irrelevant distractors. Even with forty distractors, RASTeR achieves 75{\%} accuracy, compared to the runner-up model, which reaches only 62{\%}."
}