@inproceedings{j-etal-2026-techssn,
title = "{T}ech{SSN} at {S}em{E}val-2026 Task 8: {MTRAG} Retrieval and Generation using Ensemble Re-encoders and Anchor Prompting",
author = "J, Anne Jacika and
K, Anishka and
K, Guruprakash and
Sivanaiah, Rajalakshmi and
S, Angel Deborah",
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-1.267/",
pages = "2114--2119",
ISBN = "979-8-89176-414-9",
abstract = "This paper discusses the Retrieval-Augmented Generation (RAG) system submitted to the MTRAG-UN shared task on multi-turn conversational question answering. The paper describes the proposed solution for Task A (Document Retrieval) and Task C (Full RAG Pipeline), focusing on retrieval robustness and grounded response generation in complex English multi-turn dialogs. The proposed retrieval architecture uses a cascaded hybrid pipeline, which combines sparse retrieval (BM25) with dense bi-encoder models (BGE-base-en-v1.5 and E5-base), integrated via Reciprocal Rank Fusion and refined using a weighted ensemble of cross-encoders. For the generation part, the top-3 retrieved passages are injected into FLAN-T5-Large using an anchor-prompting strategy to output grounded faithful responses. Experimental results show that the proposed hybrid retrieval framework with multi-stage reranking significantly enhances passage selection, particularly for non-standalone conversational queries. Further analysis reveals persistent difficulties in handling underspecified and unanswerable questions, as well as an increased susceptibility to retrieval noise in later dialog turns."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="j-etal-2026-techssn">
<titleInfo>
<title>TechSSN at SemEval-2026 Task 8: MTRAG Retrieval and Generation using Ensemble Re-encoders and Anchor Prompting</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anne</namePart>
<namePart type="given">Jacika</namePart>
<namePart type="family">J</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anishka</namePart>
<namePart type="family">K</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guruprakash</namePart>
<namePart type="family">K</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rajalakshmi</namePart>
<namePart type="family">Sivanaiah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Angel</namePart>
<namePart type="given">Deborah</namePart>
<namePart type="family">S</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 discusses the Retrieval-Augmented Generation (RAG) system submitted to the MTRAG-UN shared task on multi-turn conversational question answering. The paper describes the proposed solution for Task A (Document Retrieval) and Task C (Full RAG Pipeline), focusing on retrieval robustness and grounded response generation in complex English multi-turn dialogs. The proposed retrieval architecture uses a cascaded hybrid pipeline, which combines sparse retrieval (BM25) with dense bi-encoder models (BGE-base-en-v1.5 and E5-base), integrated via Reciprocal Rank Fusion and refined using a weighted ensemble of cross-encoders. For the generation part, the top-3 retrieved passages are injected into FLAN-T5-Large using an anchor-prompting strategy to output grounded faithful responses. Experimental results show that the proposed hybrid retrieval framework with multi-stage reranking significantly enhances passage selection, particularly for non-standalone conversational queries. Further analysis reveals persistent difficulties in handling underspecified and unanswerable questions, as well as an increased susceptibility to retrieval noise in later dialog turns.</abstract>
<identifier type="citekey">j-etal-2026-techssn</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.267/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>2114</start>
<end>2119</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TechSSN at SemEval-2026 Task 8: MTRAG Retrieval and Generation using Ensemble Re-encoders and Anchor Prompting
%A J, Anne Jacika
%A K, Anishka
%A K, Guruprakash
%A Sivanaiah, Rajalakshmi
%A S, Angel Deborah
%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 j-etal-2026-techssn
%X This paper discusses the Retrieval-Augmented Generation (RAG) system submitted to the MTRAG-UN shared task on multi-turn conversational question answering. The paper describes the proposed solution for Task A (Document Retrieval) and Task C (Full RAG Pipeline), focusing on retrieval robustness and grounded response generation in complex English multi-turn dialogs. The proposed retrieval architecture uses a cascaded hybrid pipeline, which combines sparse retrieval (BM25) with dense bi-encoder models (BGE-base-en-v1.5 and E5-base), integrated via Reciprocal Rank Fusion and refined using a weighted ensemble of cross-encoders. For the generation part, the top-3 retrieved passages are injected into FLAN-T5-Large using an anchor-prompting strategy to output grounded faithful responses. Experimental results show that the proposed hybrid retrieval framework with multi-stage reranking significantly enhances passage selection, particularly for non-standalone conversational queries. Further analysis reveals persistent difficulties in handling underspecified and unanswerable questions, as well as an increased susceptibility to retrieval noise in later dialog turns.
%U https://aclanthology.org/2026.semeval-1.267/
%P 2114-2119
Markdown (Informal)
[TechSSN at SemEval-2026 Task 8: MTRAG Retrieval and Generation using Ensemble Re-encoders and Anchor Prompting](https://aclanthology.org/2026.semeval-1.267/) (J et al., SemEval 2026)
ACL