@inproceedings{athanasiou-etal-2026-ails,
title = "{AILS}-{NTUA} at {S}em{E}val-2026 Task 8: Evaluating Multi-Turn {RAG} Conversations",
author = "Athanasiou, Dimosthenis and
Lymperaiou, Maria and
Filandrianos, Giorgos and
Voulodimos, Athanasios and
Stamou, Giorgos",
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-1.175/",
pages = "1340--1365",
ISBN = "979-8-89176-414-9",
abstract = "We describe the AILS-NTUA system for SemEval-2026 Task 8 (MTRAGEval), addressing all three subtasks of multi-turn retrieval-augmented generation: passage retrieval (A), reference-grounded response generation (B), and end-to-end RAG (C).Our approach is based on two main design principles. First, we adopt a query-diversity-over-retriever-diversity strategy, where multiple complementary LLM-based query reformulations are issued to a single corpus-aligned sparse retriever and combined using a variance-aware nested Reciprocal Rank Fusion scheme. Second, we employ an agentic generation pipeline that decomposes grounded response generation into evidence span extraction, dual-candidate drafting, and calibrated multi-judge selection.The proposed system achieves strong performance across subtasks, ranking first in Task A and second in Task B in the official evaluation. Our empirical findings indicate that query diversity over a well-aligned retriever is more effective than heterogeneous retriever ensembling, and that answerability calibration{---}rather than retrieval coverage{---}emerges as the primary bottleneck in end-to-end performance."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="athanasiou-etal-2026-ails">
<titleInfo>
<title>AILS-NTUA at SemEval-2026 Task 8: Evaluating Multi-Turn RAG Conversations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dimosthenis</namePart>
<namePart type="family">Athanasiou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Lymperaiou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giorgos</namePart>
<namePart type="family">Filandrianos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Athanasios</namePart>
<namePart type="family">Voulodimos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giorgos</namePart>
<namePart type="family">Stamou</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>We describe the AILS-NTUA system for SemEval-2026 Task 8 (MTRAGEval), addressing all three subtasks of multi-turn retrieval-augmented generation: passage retrieval (A), reference-grounded response generation (B), and end-to-end RAG (C).Our approach is based on two main design principles. First, we adopt a query-diversity-over-retriever-diversity strategy, where multiple complementary LLM-based query reformulations are issued to a single corpus-aligned sparse retriever and combined using a variance-aware nested Reciprocal Rank Fusion scheme. Second, we employ an agentic generation pipeline that decomposes grounded response generation into evidence span extraction, dual-candidate drafting, and calibrated multi-judge selection.The proposed system achieves strong performance across subtasks, ranking first in Task A and second in Task B in the official evaluation. Our empirical findings indicate that query diversity over a well-aligned retriever is more effective than heterogeneous retriever ensembling, and that answerability calibration—rather than retrieval coverage—emerges as the primary bottleneck in end-to-end performance.</abstract>
<identifier type="citekey">athanasiou-etal-2026-ails</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.175/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>1340</start>
<end>1365</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AILS-NTUA at SemEval-2026 Task 8: Evaluating Multi-Turn RAG Conversations
%A Athanasiou, Dimosthenis
%A Lymperaiou, Maria
%A Filandrianos, Giorgos
%A Voulodimos, Athanasios
%A Stamou, Giorgos
%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 athanasiou-etal-2026-ails
%X We describe the AILS-NTUA system for SemEval-2026 Task 8 (MTRAGEval), addressing all three subtasks of multi-turn retrieval-augmented generation: passage retrieval (A), reference-grounded response generation (B), and end-to-end RAG (C).Our approach is based on two main design principles. First, we adopt a query-diversity-over-retriever-diversity strategy, where multiple complementary LLM-based query reformulations are issued to a single corpus-aligned sparse retriever and combined using a variance-aware nested Reciprocal Rank Fusion scheme. Second, we employ an agentic generation pipeline that decomposes grounded response generation into evidence span extraction, dual-candidate drafting, and calibrated multi-judge selection.The proposed system achieves strong performance across subtasks, ranking first in Task A and second in Task B in the official evaluation. Our empirical findings indicate that query diversity over a well-aligned retriever is more effective than heterogeneous retriever ensembling, and that answerability calibration—rather than retrieval coverage—emerges as the primary bottleneck in end-to-end performance.
%U https://aclanthology.org/2026.semeval-1.175/
%P 1340-1365
Markdown (Informal)
[AILS-NTUA at SemEval-2026 Task 8: Evaluating Multi-Turn RAG Conversations](https://aclanthology.org/2026.semeval-1.175/) (Athanasiou et al., SemEval 2026)
ACL