@inproceedings{j-etal-2026-techssn,
    title = "{T}ech{SSN} at {S}em{E}val-2026 Task 8: {MTRAG} Retrieval and Generation using Ensemble Re-encoders and Anchor Prompting",
    author = "J, Anne Jacika  and
      K, Anishka  and
      K, Guruprakash  and
      Sivanaiah, Rajalakshmi  and
      S, Angel Deborah",
    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-1.267/",
    pages = "2114--2119",
    ISBN = "979-8-89176-414-9",
    abstract = "This paper discusses the Retrieval-Augmented Generation (RAG) system submitted to the MTRAG-UN shared task on multi-turn conversational question answering. The paper describes the proposed solution for Task A (Document Retrieval) and Task C (Full RAG Pipeline), focusing on retrieval robustness and grounded response generation in complex English multi-turn dialogs. The proposed retrieval architecture uses a cascaded hybrid pipeline, which combines sparse retrieval (BM25) with dense bi-encoder models (BGE-base-en-v1.5 and E5-base), integrated via Reciprocal Rank Fusion and refined using a weighted ensemble of cross-encoders. For the generation part, the top-3 retrieved passages are injected into FLAN-T5-Large using an anchor-prompting strategy to output grounded faithful responses. Experimental results show that the proposed hybrid retrieval framework with multi-stage reranking significantly enhances passage selection, particularly for non-standalone conversational queries. Further analysis reveals persistent difficulties in handling underspecified and unanswerable questions, as well as an increased susceptibility to retrieval noise in later dialog turns."
}