@inproceedings{alkhalifa-2026-optimizing,
title = "Optimizing What We Trust: Reliability-Guided {QUBO} Selection of Multi-Agent Weak Framing Signals for {A}rabic Sentiment Prediction",
author = "Alkhalifa, Rabab",
booktitle = "Proceedings of the 2nd Workshop on {NLP} for Languages Using {A}rabic Script",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.abjadnlp-1.3/",
pages = "15--25",
abstract = "Framing detection in Arabic social media is difficult due to interpretive ambiguity, cultural grounding, and limited reliable supervision. Existing LLM-based weak supervision methods typically rely on label aggregation, which is brittle when annotations are few and socially dependent. We propose a reliability-aware weak supervision framework that shifts the focus from label fusion to data curation. A small multi-agent LLM pipeline{---}two framers, a critic, and a discriminator{---}treats disagreement and reasoning quality as epistemic signals and produces instance-level reliability estimates. These estimates guide a QUBO-based subset selection procedure that enforces frame balance while reducing redundancy. Intrinsic diagnostics and an out-of-domain Arabic sentiment transfer test show that the selected subsets are more reliable and encode non-random, transferable structure, without degrading strong text-only baselines."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="alkhalifa-2026-optimizing">
<titleInfo>
<title>Optimizing What We Trust: Reliability-Guided QUBO Selection of Multi-Agent Weak Framing Signals for Arabic Sentiment Prediction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rabab</namePart>
<namePart type="family">Alkhalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on NLP for Languages Using Arabic Script</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Framing detection in Arabic social media is difficult due to interpretive ambiguity, cultural grounding, and limited reliable supervision. Existing LLM-based weak supervision methods typically rely on label aggregation, which is brittle when annotations are few and socially dependent. We propose a reliability-aware weak supervision framework that shifts the focus from label fusion to data curation. A small multi-agent LLM pipeline—two framers, a critic, and a discriminator—treats disagreement and reasoning quality as epistemic signals and produces instance-level reliability estimates. These estimates guide a QUBO-based subset selection procedure that enforces frame balance while reducing redundancy. Intrinsic diagnostics and an out-of-domain Arabic sentiment transfer test show that the selected subsets are more reliable and encode non-random, transferable structure, without degrading strong text-only baselines.</abstract>
<identifier type="citekey">alkhalifa-2026-optimizing</identifier>
<location>
<url>https://aclanthology.org/2026.abjadnlp-1.3/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>15</start>
<end>25</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Optimizing What We Trust: Reliability-Guided QUBO Selection of Multi-Agent Weak Framing Signals for Arabic Sentiment Prediction
%A Alkhalifa, Rabab
%S Proceedings of the 2nd Workshop on NLP for Languages Using Arabic Script
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%F alkhalifa-2026-optimizing
%X Framing detection in Arabic social media is difficult due to interpretive ambiguity, cultural grounding, and limited reliable supervision. Existing LLM-based weak supervision methods typically rely on label aggregation, which is brittle when annotations are few and socially dependent. We propose a reliability-aware weak supervision framework that shifts the focus from label fusion to data curation. A small multi-agent LLM pipeline—two framers, a critic, and a discriminator—treats disagreement and reasoning quality as epistemic signals and produces instance-level reliability estimates. These estimates guide a QUBO-based subset selection procedure that enforces frame balance while reducing redundancy. Intrinsic diagnostics and an out-of-domain Arabic sentiment transfer test show that the selected subsets are more reliable and encode non-random, transferable structure, without degrading strong text-only baselines.
%U https://aclanthology.org/2026.abjadnlp-1.3/
%P 15-25
Markdown (Informal)
[Optimizing What We Trust: Reliability-Guided QUBO Selection of Multi-Agent Weak Framing Signals for Arabic Sentiment Prediction](https://aclanthology.org/2026.abjadnlp-1.3/) (Alkhalifa, AbjadNLP 2026)
ACL