@inproceedings{yang-etal-2026-dutir,
title = "{DUTIR} at {S}em{E}val-2026 Task 8: A Hybrid Retrieval and Faithfulness-Guarded Framework for Multi-Turn {RAG}",
author = "Yang, Jin and
Chen, Yichong and
Yang, Liang",
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-1.48/",
pages = "328--332",
ISBN = "979-8-89176-414-9",
abstract = "This paper describes the system submittedby DUTIRtaskC for SemEval-2026 Task 8:MTRAGEval (Task C). Multi-turn RetrievalAugmented Generation (RAG) poses significant challenges in context tracking, retrievalprecision, and hallucination mitigation. Ourproposed system addresses these by employinga multi-stage pipeline consisting of: (1) LLMbased query rewriting (powered by GPT-5.2) toresolve conversational dependencies; (2) a hybrid retrieval module combining dense embeddings (BGE-M3) and sparse retrieval (BM25)with Reciprocal Rank Fusion (RRF); (3) aconfidence-based answerability gating mechanism; and (4) a post-generation faithfulnessguard. Experimental results on the blind test setshow that our approach achieves a CompositeScore of 0.5576, ranking 4th out of 29 participating teams. Detailed analysis reveals that oursystem significantly outperforms strong baselines in faithfulness and successfully handlesunderspecified queries."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2026-dutir">
<titleInfo>
<title>DUTIR at SemEval-2026 Task 8: A Hybrid Retrieval and Faithfulness-Guarded Framework for Multi-Turn RAG</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jin</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yichong</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liang</namePart>
<namePart type="family">Yang</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 system submittedby DUTIRtaskC for SemEval-2026 Task 8:MTRAGEval (Task C). Multi-turn RetrievalAugmented Generation (RAG) poses significant challenges in context tracking, retrievalprecision, and hallucination mitigation. Ourproposed system addresses these by employinga multi-stage pipeline consisting of: (1) LLMbased query rewriting (powered by GPT-5.2) toresolve conversational dependencies; (2) a hybrid retrieval module combining dense embeddings (BGE-M3) and sparse retrieval (BM25)with Reciprocal Rank Fusion (RRF); (3) aconfidence-based answerability gating mechanism; and (4) a post-generation faithfulnessguard. Experimental results on the blind test setshow that our approach achieves a CompositeScore of 0.5576, ranking 4th out of 29 participating teams. Detailed analysis reveals that oursystem significantly outperforms strong baselines in faithfulness and successfully handlesunderspecified queries.</abstract>
<identifier type="citekey">yang-etal-2026-dutir</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.48/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>328</start>
<end>332</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DUTIR at SemEval-2026 Task 8: A Hybrid Retrieval and Faithfulness-Guarded Framework for Multi-Turn RAG
%A Yang, Jin
%A Chen, Yichong
%A Yang, Liang
%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 yang-etal-2026-dutir
%X This paper describes the system submittedby DUTIRtaskC for SemEval-2026 Task 8:MTRAGEval (Task C). Multi-turn RetrievalAugmented Generation (RAG) poses significant challenges in context tracking, retrievalprecision, and hallucination mitigation. Ourproposed system addresses these by employinga multi-stage pipeline consisting of: (1) LLMbased query rewriting (powered by GPT-5.2) toresolve conversational dependencies; (2) a hybrid retrieval module combining dense embeddings (BGE-M3) and sparse retrieval (BM25)with Reciprocal Rank Fusion (RRF); (3) aconfidence-based answerability gating mechanism; and (4) a post-generation faithfulnessguard. Experimental results on the blind test setshow that our approach achieves a CompositeScore of 0.5576, ranking 4th out of 29 participating teams. Detailed analysis reveals that oursystem significantly outperforms strong baselines in faithfulness and successfully handlesunderspecified queries.
%U https://aclanthology.org/2026.semeval-1.48/
%P 328-332
Markdown (Informal)
[DUTIR at SemEval-2026 Task 8: A Hybrid Retrieval and Faithfulness-Guarded Framework for Multi-Turn RAG](https://aclanthology.org/2026.semeval-1.48/) (Yang et al., SemEval 2026)
ACL