@inproceedings{shan-etal-2026-predicting,
title = "Predicting Collective Behavior with Large Language Models: The {EBI} Framework for Response-Side Inference",
author = "Shan, Yen YU and
Chang, Li-Wun and
Ku, Lun-Wei",
editor = "Agrawal, Sweta and
Abad, Alberto",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-demos.35/",
pages = "349--358",
ISBN = "979-8-89176-461-3",
abstract = "Collective behavior forecasting usually relies on historical outcome traces: past sales, past votes, or prior campaign performance. Such history-side records are useful when comparable cases exist, but they are brittle for new products, emerging political actors, or settings where historical patterns fail to generalize. We propose a complementary response-side approach: instead of only extrapolating from past aggregate outcomes, we prompt large language models as third-party domain analysts to infer collective outcomes from structured context and behavioral signals. We introduce EBI, an Exogenous{--}Behavioral{--}Inference framework that represents each task through external context, behavioral signals, and the target aggregate outcome. Across three real-world domains {---} health supplements, elections, and crowdfunding {---} we preliminarily evaluate whether response-side inference is competitive with history-side baselines, which are restricted to historical outcome data. We present the EBI system, a web-based tool designed for users with limited access to historical data, survey infrastructure, or analyst resources, allowing them to explore domain-specific EBI predictions, run live inference across multiple models, and ablate exogenous and behavioral features interactively to understand prediction drivers."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shan-etal-2026-predicting">
<titleInfo>
<title>Predicting Collective Behavior with Large Language Models: The EBI Framework for Response-Side Inference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yen</namePart>
<namePart type="given">YU</namePart>
<namePart type="family">Shan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Li-Wun</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sweta</namePart>
<namePart type="family">Agrawal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Abad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-461-3</identifier>
</relatedItem>
<abstract>Collective behavior forecasting usually relies on historical outcome traces: past sales, past votes, or prior campaign performance. Such history-side records are useful when comparable cases exist, but they are brittle for new products, emerging political actors, or settings where historical patterns fail to generalize. We propose a complementary response-side approach: instead of only extrapolating from past aggregate outcomes, we prompt large language models as third-party domain analysts to infer collective outcomes from structured context and behavioral signals. We introduce EBI, an Exogenous–Behavioral–Inference framework that represents each task through external context, behavioral signals, and the target aggregate outcome. Across three real-world domains — health supplements, elections, and crowdfunding — we preliminarily evaluate whether response-side inference is competitive with history-side baselines, which are restricted to historical outcome data. We present the EBI system, a web-based tool designed for users with limited access to historical data, survey infrastructure, or analyst resources, allowing them to explore domain-specific EBI predictions, run live inference across multiple models, and ablate exogenous and behavioral features interactively to understand prediction drivers.</abstract>
<identifier type="citekey">shan-etal-2026-predicting</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-demos.35/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>349</start>
<end>358</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Predicting Collective Behavior with Large Language Models: The EBI Framework for Response-Side Inference
%A Shan, Yen YU
%A Chang, Li-Wun
%A Ku, Lun-Wei
%Y Agrawal, Sweta
%Y Abad, Alberto
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-461-3
%F shan-etal-2026-predicting
%X Collective behavior forecasting usually relies on historical outcome traces: past sales, past votes, or prior campaign performance. Such history-side records are useful when comparable cases exist, but they are brittle for new products, emerging political actors, or settings where historical patterns fail to generalize. We propose a complementary response-side approach: instead of only extrapolating from past aggregate outcomes, we prompt large language models as third-party domain analysts to infer collective outcomes from structured context and behavioral signals. We introduce EBI, an Exogenous–Behavioral–Inference framework that represents each task through external context, behavioral signals, and the target aggregate outcome. Across three real-world domains — health supplements, elections, and crowdfunding — we preliminarily evaluate whether response-side inference is competitive with history-side baselines, which are restricted to historical outcome data. We present the EBI system, a web-based tool designed for users with limited access to historical data, survey infrastructure, or analyst resources, allowing them to explore domain-specific EBI predictions, run live inference across multiple models, and ablate exogenous and behavioral features interactively to understand prediction drivers.
%U https://aclanthology.org/2026.emnlp-demos.35/
%P 349-358
Markdown (Informal)
[Predicting Collective Behavior with Large Language Models: The EBI Framework for Response-Side Inference](https://aclanthology.org/2026.emnlp-demos.35/) (Shan et al., EMNLP 2026)
ACL