@inproceedings{singh-das-2026-cultrag,
title = "{C}ult{RAG} at {S}em{E}val-2026 Task 7: Hybrid Sparse-Dense Retrieval with Entity-Centric Knowledge Bases for Cultural {MCQ} Answering",
author = "Singh, Aditya and
Das, Rickarya",
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-1.393/",
pages = "3137--3142",
ISBN = "979-8-89176-414-9",
abstract = "We developed CultRAG, a trust-weighted Retrieval-Augmented Generation system for BLEnD Track 2 (SemEval-2026 Task 7), targeting culturally grounded multiple-choice QA across 30 countries. Built on Llama-3.1-8B-Instruct, the six-phase pipeline integrates entity extraction via spaCy, hybrid BM25+FAISS retrieval with Reciprocal Rank Fusion, country-aware filtering, keyword-based intent detection, tiered prompt routing, anti-leak quality filtering to suppress answer-anchoring artifacts, and trust-weighted document reranking with source-credibility tiers. Ablation analysis across eight cumulative configurations and per-country decomposition identify which components contribute and where retrieval helps versus hurts, informing future directions for confidence-conditioned selective retrieval."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="singh-das-2026-cultrag">
<titleInfo>
<title>CultRAG at SemEval-2026 Task 7: Hybrid Sparse-Dense Retrieval with Entity-Centric Knowledge Bases for Cultural MCQ Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aditya</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rickarya</namePart>
<namePart type="family">Das</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 developed CultRAG, a trust-weighted Retrieval-Augmented Generation system for BLEnD Track 2 (SemEval-2026 Task 7), targeting culturally grounded multiple-choice QA across 30 countries. Built on Llama-3.1-8B-Instruct, the six-phase pipeline integrates entity extraction via spaCy, hybrid BM25+FAISS retrieval with Reciprocal Rank Fusion, country-aware filtering, keyword-based intent detection, tiered prompt routing, anti-leak quality filtering to suppress answer-anchoring artifacts, and trust-weighted document reranking with source-credibility tiers. Ablation analysis across eight cumulative configurations and per-country decomposition identify which components contribute and where retrieval helps versus hurts, informing future directions for confidence-conditioned selective retrieval.</abstract>
<identifier type="citekey">singh-das-2026-cultrag</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.393/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>3137</start>
<end>3142</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CultRAG at SemEval-2026 Task 7: Hybrid Sparse-Dense Retrieval with Entity-Centric Knowledge Bases for Cultural MCQ Answering
%A Singh, Aditya
%A Das, Rickarya
%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 singh-das-2026-cultrag
%X We developed CultRAG, a trust-weighted Retrieval-Augmented Generation system for BLEnD Track 2 (SemEval-2026 Task 7), targeting culturally grounded multiple-choice QA across 30 countries. Built on Llama-3.1-8B-Instruct, the six-phase pipeline integrates entity extraction via spaCy, hybrid BM25+FAISS retrieval with Reciprocal Rank Fusion, country-aware filtering, keyword-based intent detection, tiered prompt routing, anti-leak quality filtering to suppress answer-anchoring artifacts, and trust-weighted document reranking with source-credibility tiers. Ablation analysis across eight cumulative configurations and per-country decomposition identify which components contribute and where retrieval helps versus hurts, informing future directions for confidence-conditioned selective retrieval.
%U https://aclanthology.org/2026.semeval-1.393/
%P 3137-3142
Markdown (Informal)
[CultRAG at SemEval-2026 Task 7: Hybrid Sparse-Dense Retrieval with Entity-Centric Knowledge Bases for Cultural MCQ Answering](https://aclanthology.org/2026.semeval-1.393/) (Singh & Das, SemEval 2026)
ACL