Assessing the Impact of Conspiracy Theories Using Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jiang, Bohan, Li, Dawei, Tan, Zhen, Zhou, Xinyi, Rao, Ashwin, Lerman, Kristina, Bernard, H. Russell, Liu, Huan
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912149898526720
author Jiang, Bohan
Li, Dawei
Tan, Zhen
Zhou, Xinyi
Rao, Ashwin
Lerman, Kristina
Bernard, H. Russell
Liu, Huan
author_facet Jiang, Bohan
Li, Dawei
Tan, Zhen
Zhou, Xinyi
Rao, Ashwin
Lerman, Kristina
Bernard, H. Russell
Liu, Huan
contents Measuring the relative impact of CTs is important for prioritizing responses and allocating resources effectively, especially during crises. However, assessing the actual impact of CTs on the public poses unique challenges. It requires not only the collection of CT-specific knowledge but also diverse information from social, psychological, and cultural dimensions. Recent advancements in large language models (LLMs) suggest their potential utility in this context, not only due to their extensive knowledge from large training corpora but also because they can be harnessed for complex reasoning. In this work, we develop datasets of popular CTs with human-annotated impacts. Borrowing insights from human impact assessment processes, we then design tailored strategies to leverage LLMs for performing human-like CT impact assessments. Through rigorous experiments, we textit{discover that an impact assessment mode using multi-step reasoning to analyze more CT-related evidence critically produces accurate results; and most LLMs demonstrate strong bias, such as assigning higher impacts to CTs presented earlier in the prompt, while generating less accurate impact assessments for emotionally charged and verbose CTs.
format Preprint
id arxiv_https___arxiv_org_abs_2412_07019
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Assessing the Impact of Conspiracy Theories Using Large Language Models
Jiang, Bohan
Li, Dawei
Tan, Zhen
Zhou, Xinyi
Rao, Ashwin
Lerman, Kristina
Bernard, H. Russell
Liu, Huan
Computation and Language
Computers and Society
Measuring the relative impact of CTs is important for prioritizing responses and allocating resources effectively, especially during crises. However, assessing the actual impact of CTs on the public poses unique challenges. It requires not only the collection of CT-specific knowledge but also diverse information from social, psychological, and cultural dimensions. Recent advancements in large language models (LLMs) suggest their potential utility in this context, not only due to their extensive knowledge from large training corpora but also because they can be harnessed for complex reasoning. In this work, we develop datasets of popular CTs with human-annotated impacts. Borrowing insights from human impact assessment processes, we then design tailored strategies to leverage LLMs for performing human-like CT impact assessments. Through rigorous experiments, we textit{discover that an impact assessment mode using multi-step reasoning to analyze more CT-related evidence critically produces accurate results; and most LLMs demonstrate strong bias, such as assigning higher impacts to CTs presented earlier in the prompt, while generating less accurate impact assessments for emotionally charged and verbose CTs.
title Assessing the Impact of Conspiracy Theories Using Large Language Models
topic Computation and Language
Computers and Society
url https://arxiv.org/abs/2412.07019