Tessera
Folgen

Francesco Pierri

@frapierri.bsky.social

Assistant Professor at Politecnico di Milano. Capoeira at Sul Da Bahia Milano.

43 Posts208 Follower167 Folgt
Georg Ahnert @IC2S2@ahnert.eurosky.social · last mo.

Super excited to present our work at #ACL2026 ✨ 👉 LLM-based social simulations have lots of analytic flexibility—response generation methods are often overlooked 📍Tue July 7, 9am, Poster Session F

Georg Ahnert @IC2S2@ahnert.eurosky.social · 3mo ago

Thrilled to share that our paper with @carohaensch.bsky.social, @barbaraplank.bsky.social & @mstrohm.bsky.social has been accepted to #ACL2026 Main! How to generate closed-ended survey responses 📊 with LLMs trained to produce open-ended text? 📝 We show results from 32 mio. simulated responses… 🧵

A scientific paper titled "Survey Response Generation: Generating Closed-Ended Survey Responses In-Silico with Large Language Models", written by Georg Ahnert, Anna-Carolina Haensch, Barbara Plank, and Markus Strohmaier. Additionally, a central figure of the paper with specification curves is shown.
Christopher Barrie@cbarrie.bsky.social · 2mo ago

Very pleased to have been on the leadership team for this paper! LLMs are already being used all over behavioural science. But it is often pretty hard to work out exactly what has been done, and therefore how much confidence to place in the results. www.nature.com/articles/s41...

A reporting checklist for large language models in behavioural science - Nature Human Behaviour

Large language models offer new opportunities for behavioural science, but their rapid evolution poses challenges for research rigour. We introduce a consensus-based reporting checklist to improve tra...

nature.com

CS2Italy@cs2italy.bsky.social · 3mo ago

🔈 CS2Italy has been officially opened by @ccattuto.bsky.social at OGR Torino 🔹 AI and human behavior 🔹 Social and information networks 🔹 Urban science and mobility 🔹 Misinformation and digital platforms 🔹 Inequality, cooperation, and collective behavior 🔹 Science and society in the age of AI

Bild
EACL 2027@eaclmeeting.bsky.social · 3mo ago

📢⚠️ IMPORTANT DATE CORRECTION: the ARR deadline for EACL 2027 is Aug 3, 2026 (not Aug 6 as previously announced). EACL is earlier than usual in '27, so this is the only viable ARR cycle! 📚 All areas of CL/NLP + related fields welcome. Full CfP coming soon. #NLProc #EACL2027

EACL 2027@eaclmeeting.bsky.social · 3mo ago

Attention #NLProc researchers, the EACL 2027 website is officially LIVE: 2027.eacl.org! 🎉 🇬🇷 Join us in Athens, Greece (Mar 9-13, 2027) at #EACL2027 📅 ARR submission deadline: Aug 6, 2026. Open to all areas of CL/NLP + related fields. Stay tuned for the detailed CfP soon!

Picture of the Acropolis in Athens, Greece
Francesco Pierri@frapierri.bsky.social · 4mo ago

I am looking for highly motivated candidates for 𝟭 𝗳𝘂𝗹𝗹𝘆-𝗳𝘂𝗻𝗱𝗲𝗱 𝗣𝗵𝗗 𝗽𝗼𝘀𝗶𝘁𝗶𝗼𝗻 𝗮𝘁 𝗣𝗼𝗹𝗶𝘁𝗲𝗰𝗻𝗶𝗰𝗼 𝗱𝗶 𝗠𝗶𝗹𝗮𝗻𝗼, focusing on 𝗥𝗲𝘀𝗽𝗼𝗻𝘀𝗶𝗯𝗹𝗲 𝗔𝗜 𝗮𝗻𝗱 𝗖𝗼𝗺𝗽𝘂𝘁𝗮𝘁𝗶𝗼𝗻𝗮𝗹 𝗦𝗼𝗰𝗶𝗮𝗹 𝗦𝗰𝗶𝗲𝗻𝗰𝗲. Please share with potentially interested candidates.

ELLIS@ellis.eu · 4mo ago

🏹 Job alert: PhD position in Responsible AI/Computational Social Science at Politecnico di Milano 📍 Milan 🇮🇹 🔗 bit.ly/4dUbC4i

Elisa Bassignana@elisabassignana.bsky.social · 4mo ago

LLMs are reshaping how we process information, now even processing videos for us. In a study with 900+ participants, we found AI boosts efficiency and accuracy, but also drives overreliance. So the real question: how much of our access to information are we willing to outsource to LLMs?

Luca Maria Aiello@lajello.bsky.social · 4mo ago

AI can now answer questions about video content, transforming how people consume information on the Web. An experiment with 900+ participants found that AI improves speed and accuracy of retrieval BUT, users become overreliant on AI answers, accepting wrong answers without any loss of confidence.

A two barplots side by side.The left plot shows accuracy of information retrieval (y-axis, ranging from 0 to 100%) across three conditions (No AI, AI, and AI providing wrong answers). The right plot shows self-reported confidence in the answer correctness (y-axis, ranging from 0 to 5) across the same three conditions. Across the two plots, each condition contains two bars: one for users who watched the relevant segment of the video containing the answer to a question, and one for users who did NOT watch the segment. The plot conveys the following messages. 1) In the "No AI" condition, people who did not watch the video provide far less accurate responses. 2) In the "AI" condition, accuracy is high regardless of whether people watched the video or not. 3) in the "AI providing wrong answer" condition, accuracy drops to the minimum values for people who did not check the video. 4) Self-reported confidence in the answers is always high across all conditions, with just a tiny difference between the watched vs. non-watched scenarios
Luca Maria Aiello@lajello.bsky.social · 4mo ago

AI can now answer questions about video content, transforming how people consume information on the Web. An experiment with 900+ participants found that AI improves speed and accuracy of retrieval BUT, users become overreliant on AI answers, accepting wrong answers without any loss of confidence.

A two barplots side by side.The left plot shows accuracy of information retrieval (y-axis, ranging from 0 to 100%) across three conditions (No AI, AI, and AI providing wrong answers). The right plot shows self-reported confidence in the answer correctness (y-axis, ranging from 0 to 5) across the same three conditions. Across the two plots, each condition contains two bars: one for users who watched the relevant segment of the video containing the answer to a question, and one for users who did NOT watch the segment. The plot conveys the following messages. 1) In the "No AI" condition, people who did not watch the video provide far less accurate responses. 2) In the "AI" condition, accuracy is high regardless of whether people watched the video or not. 3) in the "AI providing wrong answer" condition, accuracy drops to the minimum values for people who did not check the video. 4) Self-reported confidence in the answers is always high across all conditions, with just a tiny difference between the watched vs. non-watched scenarios
Kevin Yang@yang3kc.bsky.social · 5mo ago

I'm organizing a Research with AI Agents Workshop Series, inviting colleagues and friends who have been actively exploring the application of AI agents to share how they're using them in their work and research. The first talk will feature Dr. Yanbo Zhang. See abstract and bio below. 1/2

Bild
Francesco Pierri@frapierri.bsky.social · 5mo ago

Due to the high number of applicants we extended the deadline by one week to **March 8th**. css2.lakecomoschool.org

Homepage - Computational Social Science

Computational Social Science: Advances, Challenges and Opportunities 2nd Edition June 22-26, 2026 Villa del Grumello, Como, Italy Over the past decade, computational social science (CSS) has risen as ...

css2.lakecomoschool.org

Francesco Pierri@frapierri.bsky.social · 5mo ago

Final call for applications - deadline on February 28th!

@icwsm.bsky.social · 5mo ago

❗Just a bit less than 4 weeks left for the Adamic-Glance Award's nominations! If you are or you know an early-career researcher who has made innovative and impactful contributions to social computing and computational social science, please consider this great opportunity ⭐️

@icwsm.bsky.social · 6mo ago

The #ICWSM 2026 Adamic-Glance Distinguished Young Researcher Award is now accepting nominations and self-nominations! 📅 Deadline for this year's award: March 15th, 2026. Don't miss out on this great opportunity! More info: icwsm.org/2026/submit....