@inproceedings{krishnasamy-wihardjo-2026-gigitai,
title = "{G}igit{AI} at {S}em{E}val-2026 Task 8: Hybrid Sparse-Dense Retrieval and Zero-Shot Generation for Multi-Turn Conversational {RAG}",
author = "Krishnasamy, Saran and
Wihardjo, Inez",
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-1.389/",
pages = "3103--3111",
ISBN = "979-8-89176-414-9",
abstract = "We describe our system for SemEval-2026 Task 8 (MTRAGEval) on multi-turn conversational RAG. Our approach combines hybrid retrieval (fusing SPLADE-v3 learned sparse representations with dense embeddings via Reciprocal Rank Fusion) with a fine-tuned cross-encoder reranker and zero-shot LLM generation using Claude Opus 4.5. We systematically evaluate 56 retrieval configurations across 4 domains, and 5 generation strategies across 5 LLMs. Our findings show that: (1) SPLADE-v3 with dataset rewrites substantially outperforms BM25 across all configurations, (2) simple zero-shot prompting matches sophisticated strategies like Self-RAG and CRAG, and (3) performance varies significantly by answerability class. On the test set, we achieve rank 5/29 on Task C (end-to-end RAG, H=0.5564), rank 7/26 on Task B (generation, H=0.7495), and rank 13/38 on Task A (retrieval, nDCG@5=0.4782). Our analysis reveals strong performance on answerable queries (H=0.685) but degradation on underspecified queries (H=0.254)."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="krishnasamy-wihardjo-2026-gigitai">
<titleInfo>
<title>GigitAI at SemEval-2026 Task 8: Hybrid Sparse-Dense Retrieval and Zero-Shot Generation for Multi-Turn Conversational RAG</title>
</titleInfo>
<name type="personal">
<namePart type="given">Saran</namePart>
<namePart type="family">Krishnasamy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Inez</namePart>
<namePart type="family">Wihardjo</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 our system for SemEval-2026 Task 8 (MTRAGEval) on multi-turn conversational RAG. Our approach combines hybrid retrieval (fusing SPLADE-v3 learned sparse representations with dense embeddings via Reciprocal Rank Fusion) with a fine-tuned cross-encoder reranker and zero-shot LLM generation using Claude Opus 4.5. We systematically evaluate 56 retrieval configurations across 4 domains, and 5 generation strategies across 5 LLMs. Our findings show that: (1) SPLADE-v3 with dataset rewrites substantially outperforms BM25 across all configurations, (2) simple zero-shot prompting matches sophisticated strategies like Self-RAG and CRAG, and (3) performance varies significantly by answerability class. On the test set, we achieve rank 5/29 on Task C (end-to-end RAG, H=0.5564), rank 7/26 on Task B (generation, H=0.7495), and rank 13/38 on Task A (retrieval, nDCG@5=0.4782). Our analysis reveals strong performance on answerable queries (H=0.685) but degradation on underspecified queries (H=0.254).</abstract>
<identifier type="citekey">krishnasamy-wihardjo-2026-gigitai</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.389/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>3103</start>
<end>3111</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GigitAI at SemEval-2026 Task 8: Hybrid Sparse-Dense Retrieval and Zero-Shot Generation for Multi-Turn Conversational RAG
%A Krishnasamy, Saran
%A Wihardjo, Inez
%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 krishnasamy-wihardjo-2026-gigitai
%X We describe our system for SemEval-2026 Task 8 (MTRAGEval) on multi-turn conversational RAG. Our approach combines hybrid retrieval (fusing SPLADE-v3 learned sparse representations with dense embeddings via Reciprocal Rank Fusion) with a fine-tuned cross-encoder reranker and zero-shot LLM generation using Claude Opus 4.5. We systematically evaluate 56 retrieval configurations across 4 domains, and 5 generation strategies across 5 LLMs. Our findings show that: (1) SPLADE-v3 with dataset rewrites substantially outperforms BM25 across all configurations, (2) simple zero-shot prompting matches sophisticated strategies like Self-RAG and CRAG, and (3) performance varies significantly by answerability class. On the test set, we achieve rank 5/29 on Task C (end-to-end RAG, H=0.5564), rank 7/26 on Task B (generation, H=0.7495), and rank 13/38 on Task A (retrieval, nDCG@5=0.4782). Our analysis reveals strong performance on answerable queries (H=0.685) but degradation on underspecified queries (H=0.254).
%U https://aclanthology.org/2026.semeval-1.389/
%P 3103-3111
Markdown (Informal)
[GigitAI at SemEval-2026 Task 8: Hybrid Sparse-Dense Retrieval and Zero-Shot Generation for Multi-Turn Conversational RAG](https://aclanthology.org/2026.semeval-1.389/) (Krishnasamy & Wihardjo, SemEval 2026)
ACL