arXiv subjects

James N. Druckman

Publications and source records attributed to James N. Druckman.

4 recordsLinked to original sources

arXiv2026

Replicating Human Motivated Reasoning Studies with LLMs

Motivated reasoning - the idea that individuals processing information may be motivated to either arrive at accurate beliefs or arrive at desired conclusions - has been well-explored as a human phenomenon. However, it remains unclear whether base LLMs are affected by motivational manipulations. Replicating 4 prior political motivated reasoning studies, we find that base LLM behavior does not align with expected human behavior. Furthermore, base LLM behavior across models shares some similarities, such as when selecting to abstain from question answering and incorporating provided arguments into opinions. The results suggest that base LLMs may not emulate human motivated reasoning processes. We emphasize the importance of these findings for researchers using LLMs to for certain tasks such as opinion replication and argument assessment.

cs.HC↗

arXiv2026

Can LLMs Emulate Human Belief Dynamics?

Can LLMs simulate how humans form and change beliefs in social networks? We put this to the test by replicating an established study on belief dynamics, evaluating 12 LLMs across multiple model families and parameter sizes. The answer is a clear no, and in systematic ways. LLMs fail to capture initial human belief distributions and tend to be overall more conformist than humans, shifting their responses to align with those around them. They also take a nuanced approach to emulating human homophilic tendencies within networks. Our findings carry a double payoff: they highlight fundamental properties of LLM behavior, and they raise a sharp warning against deploying LLMs as human proxies in social simulations.

cs.SI↗

arXiv2025

Personalized Large Language Models Can Increase the Belief Accuracy of Social Networks

Large language models (LLMs) are increasingly involved in shaping public understanding on contested issues. This has led to substantial discussion about the potential of LLMs to reinforce or correct misperceptions. While existing literature documents the impact of LLMs on individuals' beliefs, limited work explores how LLMs affect social networks. We address this gap with a pre-registered experiment (N = 1265) around the 2024 US presidential election, where we empirically explore the impact of personalized LLMs on belief accuracy in the context of social networks. The LLMs are constructed to be personalized, offering messages tailored to individuals' profiles, and to have guardrails for accurate information retrieval. We find that the presence of a personalized LLM leads individuals to update their beliefs towards the truth. More importantly, individuals with a personalized LLM in their social network not only choose to follow it, indicating they would like to obtain information from it in subsequent interactions, but also construct subsequent social networks to include other individuals with beliefs similar to the LLM -- in this case, more accurate beliefs. Therefore, our results show that LLMs have the capacity to influence individual beliefs and the social networks in which people exist, and highlight the potential of LLMs to act as corrective agents in online environments. Our findings can inform future strategies for responsible AI-mediated communication.

cs.SI↗

arXiv2024

The Need for a Recurring Large-Scale Benchmarking Survey to Continually Evaluate Sampling Methods and Administration Modes: Lessons from the 2022 Collaborative Midterm Survey

As survey methods adapt to technological and societal changes, a growing body of research seeks to understand the tradeoffs associated with various sampling methods and administration modes. We show how the NSF-funded 2022 Collaborative Midterm Survey (CMS) can be used as a dynamic and transparent framework for evaluating which sampling approaches - or combination of approaches - are best suited for various research goals. The CMS is ideally suited for this purpose because it includes almost 20,000 respondents interviewed using two administration modes (phone and online) and data drawn from random digit dialing, random address-based sampling, a probability-based panel, two nonprobability panels, and two nonprobability marketplaces. The analysis considers three types of population benchmarks (election data, administrative records, and large government surveys) and focuses on the national-level estimates as well as oversamples in three states (California, Florida, and Wisconsin). In addition to documenting how each of the survey strategies performed, we develop a strategy to assess how different combinations of approaches compare to different population benchmarks in order to guide researchers combining sampling methods and sources. We conclude by providing specific recommendations to public opinion and election survey researchers and demonstrating how our approach could be applied to a large government survey conducted at regular intervals to provide ongoing guidance to researchers, government, businesses, and nonprofits regarding the most appropriate survey sampling and administration methods.

stat.OT↗