@inproceedings{ray-saksainaa-2026-momo,
title = "{M}o{M}o at {S}em{E}val-2026 Task 9: Inference-Only Prompting vs. Fine-Tuning for Multilingual Polarization Detection",
author = "Ray, Sushant and
Saksainaa, Rakshita",
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-1.440/",
pages = "3591--3601",
ISBN = "979-8-89176-414-9",
abstract = "We describe our submission to SemEval-2026 Task 9 Subtask 1, which focuses on multilingual polarization detection over the POLAR dataset. We compare three adaptation paradigms: fully fine-tuned multilingual encoders, frozen encoders augmented with lightweight residual heads, and inference-only multilingual LLM prompting in zero-shot and few-shot settings. For few-shot prompting, we evaluate both random and similarity-based support example selection. Similarity-based few-shot prompting with a multilingual LLM competes with our fine-tuned encoder baselines while requiring no task-specific training. We further analyze energy usage, stability across prompt selections and per-language behavior to characterize trade-offs between architectural adaptation and prompt-based inference. While our submission uses a fully fine tuned XLM-RoBERTa Large, the results indicate that inference-only prompting can be a competitive and energy-efficient alternative to task-specific fine-tuning in multilingual classification."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ray-saksainaa-2026-momo">
<titleInfo>
<title>MoMo at SemEval-2026 Task 9: Inference-Only Prompting vs. Fine-Tuning for Multilingual Polarization Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sushant</namePart>
<namePart type="family">Ray</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rakshita</namePart>
<namePart type="family">Saksainaa</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 submission to SemEval-2026 Task 9 Subtask 1, which focuses on multilingual polarization detection over the POLAR dataset. We compare three adaptation paradigms: fully fine-tuned multilingual encoders, frozen encoders augmented with lightweight residual heads, and inference-only multilingual LLM prompting in zero-shot and few-shot settings. For few-shot prompting, we evaluate both random and similarity-based support example selection. Similarity-based few-shot prompting with a multilingual LLM competes with our fine-tuned encoder baselines while requiring no task-specific training. We further analyze energy usage, stability across prompt selections and per-language behavior to characterize trade-offs between architectural adaptation and prompt-based inference. While our submission uses a fully fine tuned XLM-RoBERTa Large, the results indicate that inference-only prompting can be a competitive and energy-efficient alternative to task-specific fine-tuning in multilingual classification.</abstract>
<identifier type="citekey">ray-saksainaa-2026-momo</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.440/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>3591</start>
<end>3601</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MoMo at SemEval-2026 Task 9: Inference-Only Prompting vs. Fine-Tuning for Multilingual Polarization Detection
%A Ray, Sushant
%A Saksainaa, Rakshita
%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 ray-saksainaa-2026-momo
%X We describe our submission to SemEval-2026 Task 9 Subtask 1, which focuses on multilingual polarization detection over the POLAR dataset. We compare three adaptation paradigms: fully fine-tuned multilingual encoders, frozen encoders augmented with lightweight residual heads, and inference-only multilingual LLM prompting in zero-shot and few-shot settings. For few-shot prompting, we evaluate both random and similarity-based support example selection. Similarity-based few-shot prompting with a multilingual LLM competes with our fine-tuned encoder baselines while requiring no task-specific training. We further analyze energy usage, stability across prompt selections and per-language behavior to characterize trade-offs between architectural adaptation and prompt-based inference. While our submission uses a fully fine tuned XLM-RoBERTa Large, the results indicate that inference-only prompting can be a competitive and energy-efficient alternative to task-specific fine-tuning in multilingual classification.
%U https://aclanthology.org/2026.semeval-1.440/
%P 3591-3601
Markdown (Informal)
[MoMo at SemEval-2026 Task 9: Inference-Only Prompting vs. Fine-Tuning for Multilingual Polarization Detection](https://aclanthology.org/2026.semeval-1.440/) (Ray & Saksainaa, SemEval 2026)
ACL