@inproceedings{ray-gupta-2026-iitkanbdone,
title = "{IITK}an{BD}one at {S}em{E}val-2026 Task 8: {MTRAGE}val - Evaluating Multi-Turn {RAG} Conversations",
author = "Ray, Soumendra and
Gupta, Garima",
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-1.145/",
pages = "1063--1067",
ISBN = "979-8-89176-414-9",
abstract = "This paper describes our system for the MT-RAG (Multi-Turn Retrieval-Augmented Generation) shared task, which addresses the challenge of multi-turn conversational question answering using retrieval-augmented generation. We participated in three sub-tasks of Task 8: Task A (retrieval), Task B (generation with reference passages), and Task C (end-to-end RAG). For Task A, we evaluated multiple retrieval approaches including BM25, BGE, and hybrid methods, achieving best performance with ELSER (Elastic Learned Sparse EncodeR) with nDCG@5 of 0.4018 (Rank 24/38). For Task B, we employed the Mistral-7B-Instruct-v0.2 model via HuggingFace for response generation using gold reference passages, achieving a harmonic mean score of 0.6976 (Rank 13/26). For Task C, we combined ELSER retrieval with Mistral-7B generation, using top-5 retrieved passages as context, achieving a score of 0.4289 (Rank 23/29). Our system demonstrates the effectiveness of learned sparse retrieval methods and instruction-tuned models for multi-turn conversational RAG scenarios."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ray-gupta-2026-iitkanbdone">
<titleInfo>
<title>IITKanBDone at SemEval-2026 Task 8: MTRAGEval - Evaluating Multi-Turn RAG Conversations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Soumendra</namePart>
<namePart type="family">Ray</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Garima</namePart>
<namePart type="family">Gupta</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 our system for the MT-RAG (Multi-Turn Retrieval-Augmented Generation) shared task, which addresses the challenge of multi-turn conversational question answering using retrieval-augmented generation. We participated in three sub-tasks of Task 8: Task A (retrieval), Task B (generation with reference passages), and Task C (end-to-end RAG). For Task A, we evaluated multiple retrieval approaches including BM25, BGE, and hybrid methods, achieving best performance with ELSER (Elastic Learned Sparse EncodeR) with nDCG@5 of 0.4018 (Rank 24/38). For Task B, we employed the Mistral-7B-Instruct-v0.2 model via HuggingFace for response generation using gold reference passages, achieving a harmonic mean score of 0.6976 (Rank 13/26). For Task C, we combined ELSER retrieval with Mistral-7B generation, using top-5 retrieved passages as context, achieving a score of 0.4289 (Rank 23/29). Our system demonstrates the effectiveness of learned sparse retrieval methods and instruction-tuned models for multi-turn conversational RAG scenarios.</abstract>
<identifier type="citekey">ray-gupta-2026-iitkanbdone</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.145/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>1063</start>
<end>1067</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T IITKanBDone at SemEval-2026 Task 8: MTRAGEval - Evaluating Multi-Turn RAG Conversations
%A Ray, Soumendra
%A Gupta, Garima
%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 ray-gupta-2026-iitkanbdone
%X This paper describes our system for the MT-RAG (Multi-Turn Retrieval-Augmented Generation) shared task, which addresses the challenge of multi-turn conversational question answering using retrieval-augmented generation. We participated in three sub-tasks of Task 8: Task A (retrieval), Task B (generation with reference passages), and Task C (end-to-end RAG). For Task A, we evaluated multiple retrieval approaches including BM25, BGE, and hybrid methods, achieving best performance with ELSER (Elastic Learned Sparse EncodeR) with nDCG@5 of 0.4018 (Rank 24/38). For Task B, we employed the Mistral-7B-Instruct-v0.2 model via HuggingFace for response generation using gold reference passages, achieving a harmonic mean score of 0.6976 (Rank 13/26). For Task C, we combined ELSER retrieval with Mistral-7B generation, using top-5 retrieved passages as context, achieving a score of 0.4289 (Rank 23/29). Our system demonstrates the effectiveness of learned sparse retrieval methods and instruction-tuned models for multi-turn conversational RAG scenarios.
%U https://aclanthology.org/2026.semeval-1.145/
%P 1063-1067
Markdown (Informal)
[IITKanBDone at SemEval-2026 Task 8: MTRAGEval - Evaluating Multi-Turn RAG Conversations](https://aclanthology.org/2026.semeval-1.145/) (Ray & Gupta, SemEval 2026)
ACL