@inproceedings{zaghouani-2026-accountable,
title = "Accountable Human-{AI} Deliberation with {LLM}s: Scaling Collective Intelligence through Symbiotic Scaffolding",
author = "Zaghouani, Wajdi",
editor = "Anastasiou, Lucas and
Boland, Katarina and
Liddo, Anna De and
Falk, Neele and
Hautli-Janisz, Annette and
Lapesa, Gabriella and
Romberg, Julia",
booktitle = "Proceedings of The 2nd Workshop on Language-driven Deliberation Technology",
month = may,
year = "2026",
address = "Mallorca, Spain",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.delite-1.2/",
doi = "10.63317/37crtjgcefv3",
pages = "7--17",
abstract = "Large language models (LLMs) can support democratic deliberation at scales previously constrained by turn-taking and facilitation bandwidth. Recent work shows that LLM-generated group statements are often preferred over human-mediated outputs, while theoretical analyses argue that LLMs relax the simultaneity constraints limiting collective intelligence. Yet pure LLM mediation risks collapsing pluralism, over-optimizing for agreement, and undermining legitimacy when participants cannot contest how they are represented. We propose a symbiotic human-AI framework organized into three layers: observation and diversity amplification, facilitation with clause-level provenance, and human primacy for ratification. Our contributions include graded coverage, diversity, and erasure metrics with salience-aware weighting; a provenance pipeline combining cross-encoder similarity with causal knockout diagnostics; preference-conditioned trade-off control; equity-aware contestability workflows; adversarial robustness tests; and an evaluation protocol with ablation designs informed by evidence of LLM-as-judge limitations. The result is a testable blueprint for deliberation technology that scales collective intelligence while preserving agency and legitimacy."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zaghouani-2026-accountable">
<titleInfo>
<title>Accountable Human-AI Deliberation with LLMs: Scaling Collective Intelligence through Symbiotic Scaffolding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wajdi</namePart>
<namePart type="family">Zaghouani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of The 2nd Workshop on Language-driven Deliberation Technology</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lucas</namePart>
<namePart type="family">Anastasiou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katarina</namePart>
<namePart type="family">Boland</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="given">De</namePart>
<namePart type="family">Liddo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Neele</namePart>
<namePart type="family">Falk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Annette</namePart>
<namePart type="family">Hautli-Janisz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriella</namePart>
<namePart type="family">Lapesa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julia</namePart>
<namePart type="family">Romberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large language models (LLMs) can support democratic deliberation at scales previously constrained by turn-taking and facilitation bandwidth. Recent work shows that LLM-generated group statements are often preferred over human-mediated outputs, while theoretical analyses argue that LLMs relax the simultaneity constraints limiting collective intelligence. Yet pure LLM mediation risks collapsing pluralism, over-optimizing for agreement, and undermining legitimacy when participants cannot contest how they are represented. We propose a symbiotic human-AI framework organized into three layers: observation and diversity amplification, facilitation with clause-level provenance, and human primacy for ratification. Our contributions include graded coverage, diversity, and erasure metrics with salience-aware weighting; a provenance pipeline combining cross-encoder similarity with causal knockout diagnostics; preference-conditioned trade-off control; equity-aware contestability workflows; adversarial robustness tests; and an evaluation protocol with ablation designs informed by evidence of LLM-as-judge limitations. The result is a testable blueprint for deliberation technology that scales collective intelligence while preserving agency and legitimacy.</abstract>
<identifier type="citekey">zaghouani-2026-accountable</identifier>
<identifier type="doi">10.63317/37crtjgcefv3</identifier>
<location>
<url>https://aclanthology.org/2026.delite-1.2/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>7</start>
<end>17</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Accountable Human-AI Deliberation with LLMs: Scaling Collective Intelligence through Symbiotic Scaffolding
%A Zaghouani, Wajdi
%Y Anastasiou, Lucas
%Y Boland, Katarina
%Y Liddo, Anna De
%Y Falk, Neele
%Y Hautli-Janisz, Annette
%Y Lapesa, Gabriella
%Y Romberg, Julia
%S Proceedings of The 2nd Workshop on Language-driven Deliberation Technology
%D 2026
%8 May
%I Association for Computational Linguistics
%C Mallorca, Spain
%F zaghouani-2026-accountable
%X Large language models (LLMs) can support democratic deliberation at scales previously constrained by turn-taking and facilitation bandwidth. Recent work shows that LLM-generated group statements are often preferred over human-mediated outputs, while theoretical analyses argue that LLMs relax the simultaneity constraints limiting collective intelligence. Yet pure LLM mediation risks collapsing pluralism, over-optimizing for agreement, and undermining legitimacy when participants cannot contest how they are represented. We propose a symbiotic human-AI framework organized into three layers: observation and diversity amplification, facilitation with clause-level provenance, and human primacy for ratification. Our contributions include graded coverage, diversity, and erasure metrics with salience-aware weighting; a provenance pipeline combining cross-encoder similarity with causal knockout diagnostics; preference-conditioned trade-off control; equity-aware contestability workflows; adversarial robustness tests; and an evaluation protocol with ablation designs informed by evidence of LLM-as-judge limitations. The result is a testable blueprint for deliberation technology that scales collective intelligence while preserving agency and legitimacy.
%R 10.63317/37crtjgcefv3
%U https://aclanthology.org/2026.delite-1.2/
%U https://doi.org/10.63317/37crtjgcefv3
%P 7-17
Markdown (Informal)
[Accountable Human-AI Deliberation with LLMs: Scaling Collective Intelligence through Symbiotic Scaffolding](https://aclanthology.org/2026.delite-1.2/) (Zaghouani, DELITE 2026)
ACL