@inproceedings{sivanaiah-etal-2026-ragonauts,
title = "{RAG}onauts at {S}em{E}val-2026 Task 8: {BM}25 Retrieval with Last-Turn Query Formulation for Multi-Turn {RAG} Conversations",
author = "Sivanaiah, Rajalakshmi and
S, Angel Deborah and
C, Karthik Raja and
S, Rithika",
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://aclanthology.org/2026.semeval-1.243/",
pages = "1938--1943",
ISBN = "979-8-89176-414-9",
abstract = "This paper describes the submission to Task{\textasciitilde}A of SemEval-2026 Task{\textasciitilde}8: MTRAGEval, which evaluates passage retrieval for multi-turn Retrieval-Augmented Generation (RAG) conversations across multiple knowledge domains. The task requires retrieving relevant supporting passages given conversational history, where user queries often contain implicit references and incomplete contextual information. This paper proposes a lightweight and training-free retrieval framework based on BM25 ranking combined with conversational query formulation. Queries are derived from dialogue turns and retrieval is performed using domain-specific indices to preserve corpus relevance. Without neural retrievers or fine-tuning, our system achieves an nDCG@5 score of 0.2836 on the official evaluation set, ranking 33{\textbackslash}textsuperscript{\{}rd{\}} on the leaderboard. This result demonstrates that sparse lexical retrieval remains an efficient and reproducible baseline for conversational RAG systems."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sivanaiah-etal-2026-ragonauts">
<titleInfo>
<title>RAGonauts at SemEval-2026 Task 8: BM25 Retrieval with Last-Turn Query Formulation for Multi-Turn RAG Conversations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rajalakshmi</namePart>
<namePart type="family">Sivanaiah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Angel</namePart>
<namePart type="given">Deborah</namePart>
<namePart type="family">S</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karthik</namePart>
<namePart type="given">Raja</namePart>
<namePart type="family">C</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rithika</namePart>
<namePart type="family">S</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th International Workshop on Semantic Evaluation (2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Kochmar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debanjan</namePart>
<namePart type="family">Ghosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="family">North</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mamoru</namePart>
<namePart type="family">Komachi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-414-9</identifier>
</relatedItem>
<abstract>This paper describes the submission to Task~A of SemEval-2026 Task~8: MTRAGEval, which evaluates passage retrieval for multi-turn Retrieval-Augmented Generation (RAG) conversations across multiple knowledge domains. The task requires retrieving relevant supporting passages given conversational history, where user queries often contain implicit references and incomplete contextual information. This paper proposes a lightweight and training-free retrieval framework based on BM25 ranking combined with conversational query formulation. Queries are derived from dialogue turns and retrieval is performed using domain-specific indices to preserve corpus relevance. Without neural retrievers or fine-tuning, our system achieves an nDCG@5 score of 0.2836 on the official evaluation set, ranking 33\textbackslashtextsuperscript{rd} on the leaderboard. This result demonstrates that sparse lexical retrieval remains an efficient and reproducible baseline for conversational RAG systems.</abstract>
<identifier type="citekey">sivanaiah-etal-2026-ragonauts</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.243/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>1938</start>
<end>1943</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T RAGonauts at SemEval-2026 Task 8: BM25 Retrieval with Last-Turn Query Formulation for Multi-Turn RAG Conversations
%A Sivanaiah, Rajalakshmi
%A S, Angel Deborah
%A C, Karthik Raja
%A S, Rithika
%Y Kochmar, Ekaterina
%Y Ghosh, Debanjan
%Y North, Kai
%Y Komachi, Mamoru
%S Proceedings of the 20th International Workshop on Semantic Evaluation (2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-414-9
%F sivanaiah-etal-2026-ragonauts
%X This paper describes the submission to Task~A of SemEval-2026 Task~8: MTRAGEval, which evaluates passage retrieval for multi-turn Retrieval-Augmented Generation (RAG) conversations across multiple knowledge domains. The task requires retrieving relevant supporting passages given conversational history, where user queries often contain implicit references and incomplete contextual information. This paper proposes a lightweight and training-free retrieval framework based on BM25 ranking combined with conversational query formulation. Queries are derived from dialogue turns and retrieval is performed using domain-specific indices to preserve corpus relevance. Without neural retrievers or fine-tuning, our system achieves an nDCG@5 score of 0.2836 on the official evaluation set, ranking 33\textbackslashtextsuperscript{rd} on the leaderboard. This result demonstrates that sparse lexical retrieval remains an efficient and reproducible baseline for conversational RAG systems.
%U https://aclanthology.org/2026.semeval-1.243/
%P 1938-1943Markdown (Informal)
[RAGonauts at SemEval-2026 Task 8: BM25 Retrieval with Last-Turn Query Formulation for Multi-Turn RAG Conversations](https://aclanthology.org/2026.semeval-1.243/) (Sivanaiah et al., SemEval 2026)
ACL