Francesco Salvi
@frasalvi.bsky.social
PhD Student @ Princeton CITP | Computational Social Science, NLP, Network Science, Politics | he/him | https://frasalvi.github.io/
I also have another preprint out showing similar results on Claude Sonnet 3.5 in interactive quizzes with highly incentivised humans, both in truthful and deceptive persuasion. More on this at: arxiv.org/abs/2505.09662
Large Language Models Are More Persuasive Than Incentivized Human Persuaders
We directly compare the persuasion capabilities of a frontier large language model (LLM; Claude Sonnet 3.5) against incentivized human persuaders in an interactive, real-time conversational quiz setti...
arxiv.org
May 19, 2025 at 4:29 PM
I also have another preprint out showing similar results on Claude Sonnet 3.5 in interactive quizzes with highly incentivised humans, both in truthful and deceptive persuasion. More on this at: arxiv.org/abs/2505.09662
If you're interested in knowing more, you can find a more detailed breakdown on our methodology and results at: x.com/fraslv/statu...
Or read the full paper at nature.com/articles/s41...
Thanks to my amazing coauthors @manoelhortaribeiro.bsky.social @ricgallotti.bsky.social Robert West
Or read the full paper at nature.com/articles/s41...
Thanks to my amazing coauthors @manoelhortaribeiro.bsky.social @ricgallotti.bsky.social Robert West
Francesco Salvi on X: "📢🚨Excited to share our new pre-print: “On the Conversational Persuasiveness of Large Language Models: A Randomized Controlled Trial”, with @manoelribeiro, @ricgallotti, and @cervisiarius. https://t.co/wNRMFtgCrN A thread 🧵: https://t.co/BKNbnI8avV" / X
📢🚨Excited to share our new pre-print: “On the Conversational Persuasiveness of Large Language Models: A Randomized Controlled Trial”, with @manoelribeiro, @ricgallotti, and @cervisiarius. https://t.co/wNRMFtgCrN A thread 🧵: https://t.co/BKNbnI8avV
x.com
May 19, 2025 at 4:29 PM
If you're interested in knowing more, you can find a more detailed breakdown on our methodology and results at: x.com/fraslv/statu...
Or read the full paper at nature.com/articles/s41...
Thanks to my amazing coauthors @manoelhortaribeiro.bsky.social @ricgallotti.bsky.social Robert West
Or read the full paper at nature.com/articles/s41...
Thanks to my amazing coauthors @manoelhortaribeiro.bsky.social @ricgallotti.bsky.social Robert West
That raises urgent questions about possible misuse in political propaganda, misinformation, and election interference.
Platforms and regulators should seriously consider these risks and step up in our discussion about guardrails, transparency, and accountability.
Platforms and regulators should seriously consider these risks and step up in our discussion about guardrails, transparency, and accountability.
May 19, 2025 at 4:29 PM
That raises urgent questions about possible misuse in political propaganda, misinformation, and election interference.
Platforms and regulators should seriously consider these risks and step up in our discussion about guardrails, transparency, and accountability.
Platforms and regulators should seriously consider these risks and step up in our discussion about guardrails, transparency, and accountability.
Reposted by Francesco Salvi
If your NSF grant has been terminated, please, please report it here:
airtable.com/appGKlSVeXni...
Collecting this information is supremely helpful to organize and facilitate a response.
airtable.com/appGKlSVeXni...
Collecting this information is supremely helpful to organize and facilitate a response.
April 21, 2025 at 7:59 PM
If your NSF grant has been terminated, please, please report it here:
airtable.com/appGKlSVeXni...
Collecting this information is supremely helpful to organize and facilitate a response.
airtable.com/appGKlSVeXni...
Collecting this information is supremely helpful to organize and facilitate a response.