Using Grok to Avoid Personal Attacks While Correcting Misinformation on X

TL;DR

This paper shows that using the native large language model Grok on X to correct misinformation significantly reduces hostile ad hominem attacks compared to direct human responses, potentially improving online discourse.

Contribution

It provides empirical evidence that AI-mediated corrections via Grok decrease hostility in misinformation responses, a novel approach to improving online interactions.

Findings

72% of human corrections received ad hominem attacks

Grok-mediated corrections received no ad hominem attacks

Statistically significant reduction in hostility with AI mediation

Abstract

Correcting misinformation in public online spaces often exposes users to hostility and ad hominem attacks, discouraging participation in corrective discourse. This study presents empirical evidence that invoking Grok, the native large language model on X, rather than directly confronting other users, is associated with different social responses during misinformation correction. Using an observational design, 100 correction replies across five high-conflict misinformation topics were analyzed, with corrections balanced between Grok-mediated and direct human-issued responses. The primary outcome was whether a correction received at least one ad hominem attack within a 24-hour window. Ad hominem attacks occurred in 72 percent of human-issued corrections and in none of the Grok-mediated corrections. A chi-square test confirmed a statistically significant association with a large effect size. These findings suggest that AI-mediated correction may alter the social dynamics of public disagreement by reducing interpersonal hostility during misinformation responses.