iiinova — where your digital self keeps evolving

Beyza Bozdag @beyzabozdag.bsky.social · 13/05/2025

[4/5] We'll also be maintaining a GitHub repository for computational persuasion research. Datasets, code, and resources will be included! Contributions and collaborations are warmly welcomed! 🚀 Check it out: github.com/beyzabozdag/...

130 3

Beyza Bozdag @beyzabozdag.bsky.social · 13/05/2025

[3/5] We introduce a taxonomy for computational persuasion research, highlight critical challenges, and map out future directions for safe, fair, and effective persuasive AI systems.

120 2

Beyza Bozdag @beyzabozdag.bsky.social · 13/05/2025

[2/5] We structure computational persuasion around three key perspectives: 🤖 AI as Persuader: Generating persuasive content. 🎯 AI as Persuadee: Vulnerability to persuasive influence. ⚖️ AI as Persuasion Judge: Detecting persuasive tactics and ethical concerns.

120 2

Beyza Bozdag @beyzabozdag.bsky.social · 13/05/2025

Thrilled to announce our new survey that explores the exciting possibilities and troubling risks of computational persuasion in the era of LLMs 🤖💬 📄Arxiv: arxiv.org/pdf/2505.07775 💻 GitHub: github.com/beyzabozdag/...

195 9

Beyza Bozdag @beyzabozdag.bsky.social · 04/03/2025

[6/6] Huge thanks to my amazing co-authors @shuhaib.bsky.social, @gokhantur.bsky.social, @dilekh.bsky.social and my lab @convai-uiuc.bsky.social for their help and support! 🎉 Excited to continue exploring LLM persuasiveness & AI safety! Let’s keep the conversation going! 💬

020 2

Beyza Bozdag @beyzabozdag.bsky.social · 04/03/2025

[5/6] So, who wins the persuasion game? 🏆 🤖 Llama-3.3-70B & GPT-4o show similar persuasive effectiveness 🔒 GPT-4o is 50% more resistant to misinformation persuasion vs. Llama-3.3-70B ⚖️ Some models are persuasive, but also too susceptible to persuasion!

120 2

Beyza Bozdag @beyzabozdag.bsky.social · 04/03/2025

[4/6] How does agreement shift over a conversation? 📈 ✅ Multi-turn persuasion boosts effectiveness—more chances to influence the Persuadee mean higher agreement over time!

120 2

Beyza Bozdag @beyzabozdag.bsky.social · 04/03/2025

[3/6] We evaluate persuasion across three setups: 📌 Subjective w/ Single-turn 📌 Subjective w/ Multi-turn 📌 Misinformation w/ Multi-turn (⚠️ adversarial!) 💡 Key finding: Persuasive effectiveness stays fairly stable, but susceptibility varies significantly based on the domain!

120 2

Beyza Bozdag @beyzabozdag.bsky.social · 04/03/2025

[2/6] To assess persuasive effectiveness and susceptibility, we introduce PMIYC — a scalable, automated approach where: 🤖 A Persuader tries to convince the other agent 🤖 A Persuadee updates its agreement over a multi-turn conversation Each model debates against the others!🔄

120 2

Beyza Bozdag @beyzabozdag.bsky.social · 04/03/2025

[1/6] Can LLMs out-persuade each other? 🤖🧠💬 Introducing Persuade Me If You Can (PMIYC)—a new framework to evaluate (1) how persuasive LLMs are and (2) how easily they can be persuaded! 🚀 📄Arxiv: arxiv.org/abs/2503.01829 🌐Project Page: beyzabozdag.github.io/PMIYC/

192 9

Beyza Bozdag @beyzabozdag.bsky.social · 20/11/2024

Hi, can I be added as well, thanks!

110 1

Beyza Bozdag @beyzabozdag.bsky.social · 19/11/2024

✋ I'd like to be added too, thanks!

010 1

Reposted by Beyza Bozdag

ConvAI @ UIUC @convai-uiuc.bsky.social · 17/11/2024

We had so much fun at #EMNLP2024 during the poster sessions and in Miami 🎉🎉 Evidence of fun (excursion to the south beach! 🏖️):

0123 12