萌妹社区

May 19, 2025

ChatGPT shown to be more persuasive than people in online debates

Credit: Unsplash/CC0 Public Domain
× close
Credit: Unsplash/CC0 Public Domain

Large language models (LLMs), such as GPT-4, are found to be more persuasive than humans 64% of the time in online debates when adapting their arguments on the basis of personalized information about their opponents, according to a study in Nature Human Behaviour.

The findings highlight the ability of GPT-4 to produce tailored persuasive arguments and suggest the need for further research into mitigating risks associated with their use in persuasion.

As conversations between humans and LLMs have become more common, research suggests that LLMs could become more persuasive (able to alter someone's belief or opinions). However, it has not been clear whether these models can adapt to personalized information to target arguments to specific debating opponents.

Francesco Salvi and colleagues matched 900 people in the U.S. with either another human or GPT-4 to debate various sociopolitical issues, such as whether the U.S. should ban fossil fuels. In some pairs, the opponent (whether AI or human) was given about their debate partner鈥攊ncluding their gender, age, ethnicity, , employment status, and extracted from participant surveys鈥攖o better target their arguments.

The debates took place in a controlled online setting, with participants recruited via a crowdsourcing platform specifically for the study. When equipped with personal information about participants, Salvi and colleagues found that GPT-4 was 64.4% more persuasive than human opponents. However, without access to , GPT-4's persuasive capabilities were indistinguishable from those of humans.

The authors note that limitations of the study include the debate taking a structured approach鈥攚hereas real-world debates can be more freeform鈥攁nd that the debates featured a time limit. They note the findings highlight the potential for AI-driven tools to influence human opinion, which could have implications for online platform design.

More information: Francesco Salvi et al, On the conversational persuasiveness of GPT-4, Nature Human Behaviour (2025).

Journal information: Nature Human Behaviour

Load comments (0)

This article has been reviewed according to Science X's and . have highlighted the following attributes while ensuring the content's credibility:

fact-checked
peer-reviewed publication
trusted source
proofread

Get Instant Summarized Text (GIST)

GPT-4 demonstrates greater persuasiveness than humans in online debates 64.4% of the time when provided with personalized demographic information about opponents. Without such data, its persuasive ability matches that of humans. These results underscore the potential influence of AI-driven tools on opinion formation and highlight associated risks.

This summary was automatically generated using LLM.