Henry George Xu

Henry George Xu

Auto-generated profile, based on publicly available information

Henry George Xu

Massachusetts Institute of Technology, Cambridge, MA, USA

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
14 September 2024
Verified
Book Chapter
Closed access
PDF file
PPPatrick S. Park
Patrick S. Park
HXHenry George Xu
Henry George Xu
KCKathleen M. Carley
Kathleen M. Carley

25 June 2026 in PsyArXiv
Verified
Preprint
Open access
GCGabriela Czarnek
Gabriela Czarnek
ROReed Orchinik
Reed Orchinik
HLHause Lin
Hause Lin
HXHenry George Xu
Henry George Xu
TCThomas Costello
Thomas Costello
DRDavid Rand
David Rand
Generic climate communication interventions often have modest effects on beliefs and very limited effects on climate action. We, thus, ask whether facts and evidence - tailored by an AI (a large language model, LLM) to address each person’s specific reservations - can address climate skepticism and inaction. Across two experiments, participants first described their main climate change reservation and then either engaged in a dialogue with an LLM (GPT-4-turbo) addressing it, discussed an unrelated topic with an LLM before receiving information about the scientific consensus on climate change (“standard-of-care”), or discussed an unrelated topic with an LLM alone (control; included only in the first experiment). We find that the LLM treatment substantially reduces participants’ conviction in their specific reservations, while the effects of consensus messaging are non-significant. Both treatments have effects, albeit small, on general pro-climate beliefs and attitudes. Critically, we find that the LLM treatment is more effective particularly for increasing willingness to make sacrifices to address climate change and donations to a pro-climate charity. These findings demonstrate that conversations with an AI may be an effective climate communication strategy, if people choose to interact with the bot.

17 February 2026 in PsyArXiv
Verified
Preprint
Open access
HXHenry George Xu
Henry George Xu
TCThomas H Costello
Thomas H Costello
JSJason L. Schwartz
Jason L. Schwartz
LNLinda M. Niccolai
Linda M. Niccolai
GPGordon Pennycook
Gordon Pennycook
DRDavid Rand
David Rand
BackgroundHPV vaccination rates in the United States remain substantially below the 80% target of Healthy People 2030. New approaches for increasing vaccination rates are needed. We tested whether brief text conversations with the artificial intelligence large language model (LLM) GPT-4 Turbo could significantly increase intentions to vaccinate children against HPV.MethodsWe conducted a pre-registered randomized clinical trial in which participants were assigned to a text conversation with GPT-4 Turbo in which the LLM (with no specific training) tried to persuade them to vaccinate against HPV, a CDC informational brochure, or a control conversation with the LLM about an unrelated topic. In October 2025, we recruited 7368 Americans via Cint Exchange who had unvaccinated eligible children or did not yet have children, and whose intentions to vaccinate their children against HPV was under 75 on a 0-100 scale. Participants completed pre- and post-intervention measures of HPV vaccination intentions for sons and daughters. Randomization was via Qualtrics, with no masking possible. Our primary outcome was change in HPV vaccination intentions.FindingsThe AI-dialogue significantly increased vaccination intentions relative to the control (sons: 9.73 points, 95% CI [6.89, 12.56], p < .001; daughters: 7.72 points, 95% CI [4.98, 10.46], p < .001); as did the brochure (sons: 8.04 points, 95% CI [4.83, 11.25], p < .001; daughters: 5.51 points, 95% CI [2.52, 8.50], p < .001). The differences between the AI-dialogue and the brochure were not statistically significant (sons, p = .268; daughters, p = .120). Post-assignment attrition rates did not significantly differ between treatment arms (AI-dialgue, 11.9pp; brochure, 14.2pp), although both arms had significantly more attrition than the control (5.1pp); our results were robust to baseline-carried-forward imputation. Post-hoc analysis found that the AI-dialogue was significantly more likely than the CDC brochure to produce large increases in vaccination intentions (e.g. >30 points). Fact-checking of all 15,559 AI-generated claims using an independent AI model with web search capability revealed high overall accuracy (median = 100/100, mean = 95.4/100 on a scale where 0 = completely inaccurate and 100 = completely accurate), with only 0.4% of claims being medically inaccurate.InterpretationDialogues with GPT-4 Turbo offer a potential strategy for increasing HPV vaccination intentions at scale.

10 November 2025
Verified
Conference Paper
Open access
HXHenry Xu
Henry Xu
KYKaty Yu
Katy Yu
HHHao He
Hao He
HFHongbo Fang
Hongbo Fang
BVBogdan Vasilescu
Bogdan Vasilescu
PPPatrick S. Park
Patrick S. Park