@inproceedings{elchafei-etal-2026-h,
    title = "{H}-{RAG} at {S}em{E}val-2026 Task 8: Hierarchical Parent{--}Child Retrieval for Multi-Turn {RAG} Conversations",
    author = "Elchafei, Passant  and
      Emam, Hossam  and
      Alansary, Mohamed  and
      Swain, Monorama  and
      Schedl, Markus",
    editor = "Kochmar, Ekaterina  and
      Ghosh, Debanjan  and
      North, Kai  and
      Komachi, Mamoru",
    booktitle = "Proceedings of the 20th {I}nternational {W}orkshop on {S}emantic {E}valuation (2026)",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.semeval-1.155/",
    pages = "1136--1143",
    ISBN = "979-8-89176-414-9",
    abstract = "We present H-RAG, our submission to SemEval-2026 Task 8 (MTRAGEval), addressing both Task A (Retrieval) and Task C (Generation with Retrieved Passages). Task A evaluates standalone retrieval quality, while Task C assesses end-to-end retrieval-augmented generation (RAG) in multi-turn conversational settings, requiring both accurate answer generation and faithful grounding in retrieved evidence. Our approach implements a hierarchical parent{--}child RAG pipeline that separates fine-grained child-level retrieval from parent-level context reconstruction during generation. Documents are segmented into overlapping sentence-based child chunks, while full documents are preserved as parent units to provide coherent context. weighting, and embedding-based similarity rescoring over child chunks. Retrieved evidence is aggregated at the parent level and supplied to an instruction-tuned language model for response generation. H-RAG achieves an nDCG@5 score of 0.4271 on Task A and a harmonic mean score of 0.3241 on Task C (RBagg: 0.2488, RLF: 0.2703, RBllm: 0.6508), underscoring the importance of retrieval configuration and parent-level aggregation in multi-turn RAG performance."
}