@inproceedings{zhang-etal-2026-uircis,
title = "uircis at {S}em{E}val-2026 Task 8: A Unified Lightweight Pipeline for Multi-Turn {RAG} Evaluation",
author = "Zhang, Jiaqi and
Duan, Wenbin and
Zhang, Yingqi and
Li, Yan and
Li, Binyang",
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-1.394/",
pages = "3143--3148",
ISBN = "979-8-89176-414-9",
abstract = "We submit a system description paper for SemEval-2026 Task 8 (MTRAGEval), covering both Subtask A (retrieval) and Subtask B (generation). Our approach is a lightweight, fully reproducible multi-turn RAG pipeline using open-weight models: Qwen2.5-7B-Instruct for query rewriting and grounded answer generation, BGE-M3 for dense retrieval, and BGE-Reranker-v2-M3 for cross-encoder reranking. We report official test performance, conduct ablation experiments to quantify the impact of rewriting and reranking across domains, and provide error analysis using the organizers' analytics and answerability classes, highlighting key failure modes in multi-turn retrieval specificity and grounded generation."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhang-etal-2026-uircis">
<titleInfo>
<title>uircis at SemEval-2026 Task 8: A Unified Lightweight Pipeline for Multi-Turn RAG Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiaqi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenbin</namePart>
<namePart type="family">Duan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yingqi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yan</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Binyang</namePart>
<namePart type="family">Li</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 submit a system description paper for SemEval-2026 Task 8 (MTRAGEval), covering both Subtask A (retrieval) and Subtask B (generation). Our approach is a lightweight, fully reproducible multi-turn RAG pipeline using open-weight models: Qwen2.5-7B-Instruct for query rewriting and grounded answer generation, BGE-M3 for dense retrieval, and BGE-Reranker-v2-M3 for cross-encoder reranking. We report official test performance, conduct ablation experiments to quantify the impact of rewriting and reranking across domains, and provide error analysis using the organizers’ analytics and answerability classes, highlighting key failure modes in multi-turn retrieval specificity and grounded generation.</abstract>
<identifier type="citekey">zhang-etal-2026-uircis</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.394/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>3143</start>
<end>3148</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T uircis at SemEval-2026 Task 8: A Unified Lightweight Pipeline for Multi-Turn RAG Evaluation
%A Zhang, Jiaqi
%A Duan, Wenbin
%A Zhang, Yingqi
%A Li, Yan
%A Li, Binyang
%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 zhang-etal-2026-uircis
%X We submit a system description paper for SemEval-2026 Task 8 (MTRAGEval), covering both Subtask A (retrieval) and Subtask B (generation). Our approach is a lightweight, fully reproducible multi-turn RAG pipeline using open-weight models: Qwen2.5-7B-Instruct for query rewriting and grounded answer generation, BGE-M3 for dense retrieval, and BGE-Reranker-v2-M3 for cross-encoder reranking. We report official test performance, conduct ablation experiments to quantify the impact of rewriting and reranking across domains, and provide error analysis using the organizers’ analytics and answerability classes, highlighting key failure modes in multi-turn retrieval specificity and grounded generation.
%U https://aclanthology.org/2026.semeval-1.394/
%P 3143-3148
Markdown (Informal)
[uircis at SemEval-2026 Task 8: A Unified Lightweight Pipeline for Multi-Turn RAG Evaluation](https://aclanthology.org/2026.semeval-1.394/) (Zhang et al., SemEval 2026)
ACL