@inproceedings{dutra-etal-2026-nlp,
title = "{NLP}-{CEIA}-{UFG} at {S}em{E}val-2026 Task 8: Iterative Retrieval with Notes-Guided Query Refinement for Multi-Turn {RAG}",
author = "Dutra, Guilherme and
Cara{\'i}ba, Andr{\'e} Felipe and
Da Silva, N{\'a}dia F{\'e}lix and
Dos Santos, Paulo and
Fernandes, Deborah Silva and
De Oliveira, S{\'a}vio Salvarino",
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-1.349/",
pages = "2771--2778",
ISBN = "979-8-89176-414-9",
abstract = "We describe NLP-CEIA-UFG, our system forSemEval-2026 Task 8, which evaluates multi-turn retrieval-augmented generation (RAG)over heterogeneous document corpora. Ourpipeline centers on a three-iteration dynamicretrieval loop in which two gpt-oss-120b-powered modules{---}an Iterative Query Genera-tor and a Notes Builder{---}interact at each stepto diversify queries and accumulate structurednotes on information gaps. After the loop, anAnswerability Classifier routes the query to oneof three generation paths (Complete Answer,Partial Answer, or Clarification Request). Hy-brid BM25 and dense retrieval is fused via Re-ciprocal Rank Fusion and refined by the Jinalistwise reranker. The retrieval pipeline is com-piled under DSPy and optimized with GEPA.We achieve nDCG@5 of 0.4502 (rank 17/38,Subtask A) and HM = 0.3774 (rank 24/29, Sub-task C). Post-hoc analysis identifies an over-conservative Answerability Classifier as theprimary bottleneck: 75.5{\%} of all responseswere flagged as IDK by the evaluator, includ-ing 69.8{\%} of ANSWERABLE questions, whilethe retrieval and generation components per-form well when the classifier routes correctly.Our code is available at https://github.com/GuiiCorreia/SemEval-2026."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dutra-etal-2026-nlp">
<titleInfo>
<title>NLP-CEIA-UFG at SemEval-2026 Task 8: Iterative Retrieval with Notes-Guided Query Refinement for Multi-Turn RAG</title>
</titleInfo>
<name type="personal">
<namePart type="given">Guilherme</namePart>
<namePart type="family">Dutra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">André</namePart>
<namePart type="given">Felipe</namePart>
<namePart type="family">Caraíba</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nádia</namePart>
<namePart type="given">Félix</namePart>
<namePart type="family">Da Silva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paulo</namePart>
<namePart type="family">Dos Santos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Deborah</namePart>
<namePart type="given">Silva</namePart>
<namePart type="family">Fernandes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sávio</namePart>
<namePart type="given">Salvarino</namePart>
<namePart type="family">De Oliveira</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 NLP-CEIA-UFG, our system forSemEval-2026 Task 8, which evaluates multi-turn retrieval-augmented generation (RAG)over heterogeneous document corpora. Ourpipeline centers on a three-iteration dynamicretrieval loop in which two gpt-oss-120b-powered modules—an Iterative Query Genera-tor and a Notes Builder—interact at each stepto diversify queries and accumulate structurednotes on information gaps. After the loop, anAnswerability Classifier routes the query to oneof three generation paths (Complete Answer,Partial Answer, or Clarification Request). Hy-brid BM25 and dense retrieval is fused via Re-ciprocal Rank Fusion and refined by the Jinalistwise reranker. The retrieval pipeline is com-piled under DSPy and optimized with GEPA.We achieve nDCG@5 of 0.4502 (rank 17/38,Subtask A) and HM = 0.3774 (rank 24/29, Sub-task C). Post-hoc analysis identifies an over-conservative Answerability Classifier as theprimary bottleneck: 75.5% of all responseswere flagged as IDK by the evaluator, includ-ing 69.8% of ANSWERABLE questions, whilethe retrieval and generation components per-form well when the classifier routes correctly.Our code is available at https://github.com/GuiiCorreia/SemEval-2026.</abstract>
<identifier type="citekey">dutra-etal-2026-nlp</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.349/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>2771</start>
<end>2778</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NLP-CEIA-UFG at SemEval-2026 Task 8: Iterative Retrieval with Notes-Guided Query Refinement for Multi-Turn RAG
%A Dutra, Guilherme
%A Caraíba, André Felipe
%A Da Silva, Nádia Félix
%A Dos Santos, Paulo
%A Fernandes, Deborah Silva
%A De Oliveira, Sávio Salvarino
%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 dutra-etal-2026-nlp
%X We describe NLP-CEIA-UFG, our system forSemEval-2026 Task 8, which evaluates multi-turn retrieval-augmented generation (RAG)over heterogeneous document corpora. Ourpipeline centers on a three-iteration dynamicretrieval loop in which two gpt-oss-120b-powered modules—an Iterative Query Genera-tor and a Notes Builder—interact at each stepto diversify queries and accumulate structurednotes on information gaps. After the loop, anAnswerability Classifier routes the query to oneof three generation paths (Complete Answer,Partial Answer, or Clarification Request). Hy-brid BM25 and dense retrieval is fused via Re-ciprocal Rank Fusion and refined by the Jinalistwise reranker. The retrieval pipeline is com-piled under DSPy and optimized with GEPA.We achieve nDCG@5 of 0.4502 (rank 17/38,Subtask A) and HM = 0.3774 (rank 24/29, Sub-task C). Post-hoc analysis identifies an over-conservative Answerability Classifier as theprimary bottleneck: 75.5% of all responseswere flagged as IDK by the evaluator, includ-ing 69.8% of ANSWERABLE questions, whilethe retrieval and generation components per-form well when the classifier routes correctly.Our code is available at https://github.com/GuiiCorreia/SemEval-2026.
%U https://aclanthology.org/2026.semeval-1.349/
%P 2771-2778
Markdown (Informal)
[NLP-CEIA-UFG at SemEval-2026 Task 8: Iterative Retrieval with Notes-Guided Query Refinement for Multi-Turn RAG](https://aclanthology.org/2026.semeval-1.349/) (Dutra et al., SemEval 2026)
ACL