Georg Ahnert
@wanlo.bsky.social
PhD Student in Social Data Science at University of Mannheim | LLMs and Surveys | georgahnert.de
Pinned
Georg Ahnert
@wanlo.bsky.social
· Jul 18
LLMs are trained to produce open-ended responses 📝, but most survey items require closed-ended responses instead 📊
This Wed 11:00–12:30 at #ESRA25, I'll discuss the large impact that Answer Production Methods have on prediction results + share recommendations for methods and parameters. 👈
This Wed 11:00–12:30 at #ESRA25, I'll discuss the large impact that Answer Production Methods have on prediction results + share recommendations for methods and parameters. 👈
Really excited to also present this work at #IC2S2 next week in Norrköping! 🎉 I'd love to discuss how to produce LLM survey responses at my poster on Wed at 13:30 (Poster Session 2, Poster ID 68) 📊
Reposted by Georg Ahnert
👋🏼 I'm at #EMNLP2025 presenting "The Prompt Makes the Person(a): A Systematic Evaluation of Sociodemographic Persona Prompting for LLMs"
🕑 Thu. Nov 6, 12:30 - 13:30
📍 Findings Session 2, Hall C3
🕑 Thu. Nov 6, 12:30 - 13:30
📍 Findings Session 2, Hall C3
🚨New paper alert🚨
🤔 Ever wondered how the way you write a persona prompt affects how well an LLM simulates people?
In our #EMNLP2025 paper, we find that using interview-style persona prompts makes LLM social simulations less biased and more aligned with human opinions.
🧵1/7
🤔 Ever wondered how the way you write a persona prompt affects how well an LLM simulates people?
In our #EMNLP2025 paper, we find that using interview-style persona prompts makes LLM social simulations less biased and more aligned with human opinions.
🧵1/7
November 4, 2025 at 4:39 PM
👋🏼 I'm at #EMNLP2025 presenting "The Prompt Makes the Person(a): A Systematic Evaluation of Sociodemographic Persona Prompting for LLMs"
🕑 Thu. Nov 6, 12:30 - 13:30
📍 Findings Session 2, Hall C3
🕑 Thu. Nov 6, 12:30 - 13:30
📍 Findings Session 2, Hall C3
Reposted by Georg Ahnert
🚨New paper alert🚨
🤔 Ever wondered how the way you write a persona prompt affects how well an LLM simulates people?
In our #EMNLP2025 paper, we find that using interview-style persona prompts makes LLM social simulations less biased and more aligned with human opinions.
🧵1/7
🤔 Ever wondered how the way you write a persona prompt affects how well an LLM simulates people?
In our #EMNLP2025 paper, we find that using interview-style persona prompts makes LLM social simulations less biased and more aligned with human opinions.
🧵1/7
October 31, 2025 at 5:45 PM
🚨New paper alert🚨
🤔 Ever wondered how the way you write a persona prompt affects how well an LLM simulates people?
In our #EMNLP2025 paper, we find that using interview-style persona prompts makes LLM social simulations less biased and more aligned with human opinions.
🧵1/7
🤔 Ever wondered how the way you write a persona prompt affects how well an LLM simulates people?
In our #EMNLP2025 paper, we find that using interview-style persona prompts makes LLM social simulations less biased and more aligned with human opinions.
🧵1/7
Thrilled to talk about how seemingly small decisions in silicon sampling can have a large impact on simulated survey responses 👀 Join us on Oct 29th! 👈
🚨 Upcoming #CS3Meeting 🚨
@wanlo.bsky.social talks about analytic flexibility in silicon samples on October 29, 3:15 to 4:00 PM CET).
Great opportunity to gain novel insights into how survey responses can be generated with #LLMs.
Sign up now: ww3.unipark.de/uc/cs3_meeti...
@wanlo.bsky.social talks about analytic flexibility in silicon samples on October 29, 3:15 to 4:00 PM CET).
Great opportunity to gain novel insights into how survey responses can be generated with #LLMs.
Sign up now: ww3.unipark.de/uc/cs3_meeti...
October 21, 2025 at 7:42 AM
Thrilled to talk about how seemingly small decisions in silicon sampling can have a large impact on simulated survey responses 👀 Join us on Oct 29th! 👈
Reposted by Georg Ahnert
Come join next Wednesday if you want to rant about society's love-hate relationship with LLMs!
🚨 Upcoming: "Large Language Models for Social Research: Potentials and Challenges"
👤 Indira Sen (University of Mannheim)
🗓️ Wed, October 22, 13:45-15:15 CET
📺 Register for the live stream: us02web.zoom.us/meeting/regi...
🔗 socialsciencedatalab.mzes.uni-mannheim.de/page/events/
👤 Indira Sen (University of Mannheim)
🗓️ Wed, October 22, 13:45-15:15 CET
📺 Register for the live stream: us02web.zoom.us/meeting/regi...
🔗 socialsciencedatalab.mzes.uni-mannheim.de/page/events/
![Large Language Models for Social Research: Potentials and Challenges
Hybrid event [A5, 6, Room A231 + Zoom]
Oktober 22, 2025, 13:45-15:15
Abstract
Large Language Models (LLMs) have the potential to revolutionize the social sciences—for example, by accelerating content analysis or enabling realistic social simulations. In this workshop, I will discuss how LLMs can be applied and audited for social science applications, including the generation of synthetic survey responses and content analysis. I will also address how biases in LLMs can hinder these applications and explore ways to better surface and understand these biases. Finally, I will present a hands-on use case demonstrating how LLMs can be guided using demographic personas for both content analysis and simulated surveys.
Presenter(s)
Indira Sen is a Junior Faculty member at the University of Mannheim’s Business School in the Chair of Data Science for the Social and Economic Sciences. Her work lies at the intersection of NLP and Computational Social Science, specifically in developing and evaluating representative and equitable language technology, including Large Language Models.](https://cdn.bsky.app/img/feed_thumbnail/plain/did:plc:oizrkjzyr6vekl76tjctghcl/bafkreigj6rty2hy4hgawqzq34a24si45dxzutezuphif3hprnl5amxldoy@jpeg)
October 16, 2025 at 9:32 AM
Come join next Wednesday if you want to rant about society's love-hate relationship with LLMs!
Reposted by Georg Ahnert
👋 #ACL2025NLP 🇦🇹 @marlutz.bsky.social and I are presenting our poster on demographic representativeness of LLMs today!
🕦 10:30-12:00
📍 Hall X5 (board 1 or 14 according to different sources 🧐)
Here’s the paper on ACL anthology: aclanthology.org/2025.finding...
Drop by!
🕦 10:30-12:00
📍 Hall X5 (board 1 or 14 according to different sources 🧐)
Here’s the paper on ACL anthology: aclanthology.org/2025.finding...
Drop by!
July 29, 2025 at 7:31 AM
👋 #ACL2025NLP 🇦🇹 @marlutz.bsky.social and I are presenting our poster on demographic representativeness of LLMs today!
🕦 10:30-12:00
📍 Hall X5 (board 1 or 14 according to different sources 🧐)
Here’s the paper on ACL anthology: aclanthology.org/2025.finding...
Drop by!
🕦 10:30-12:00
📍 Hall X5 (board 1 or 14 according to different sources 🧐)
Here’s the paper on ACL anthology: aclanthology.org/2025.finding...
Drop by!
Reposted by Georg Ahnert
All the keynote recordings are available now, enjoy! www.youtube.com/playlist?lis...
IC2S2'25 Norrköping - YouTube
This playlist contains all keynotes from IC2S2'25 in Norrköping, Sweden.
www.youtube.com
July 25, 2025 at 3:49 PM
All the keynote recordings are available now, enjoy! www.youtube.com/playlist?lis...
Reposted by Georg Ahnert
Chair for Data Science in the Economic and Social Sciences at University of Mannheim having lots of fun at #ic2s2 @janajung.bsky.social @wanlo.bsky.social @indiiigo.bsky.social @jrupprec.bsky.social @maximiliankreutner.bsky.social and Stefano Balietti
July 23, 2025 at 3:22 PM
Chair for Data Science in the Economic and Social Sciences at University of Mannheim having lots of fun at #ic2s2 @janajung.bsky.social @wanlo.bsky.social @indiiigo.bsky.social @jrupprec.bsky.social @maximiliankreutner.bsky.social and Stefano Balietti
Really inspiring keynote by @lauraknelson.bsky.social this morning at #IC2S2 discussing when to model and when to generate societies—among many other themes in computational qualitative research!
July 23, 2025 at 8:00 AM
Really inspiring keynote by @lauraknelson.bsky.social this morning at #IC2S2 discussing when to model and when to generate societies—among many other themes in computational qualitative research!
Reposted by Georg Ahnert
Before heading to ACL, I'm excited to be at #IC2S2 this week! 🌞
I'll present a related working paper on validating LLM social simulations at the ABM session on Tuesday (11 AM, Vingen 7): indiiigo.github.io/files/GABM_V...
(w/ @wanlo.bsky.social @mstrohm.bsky.social and @janalasser.bsky.social)
I'll present a related working paper on validating LLM social simulations at the ABM session on Tuesday (11 AM, Vingen 7): indiiigo.github.io/files/GABM_V...
(w/ @wanlo.bsky.social @mstrohm.bsky.social and @janalasser.bsky.social)
July 21, 2025 at 8:00 PM
Before heading to ACL, I'm excited to be at #IC2S2 this week! 🌞
I'll present a related working paper on validating LLM social simulations at the ABM session on Tuesday (11 AM, Vingen 7): indiiigo.github.io/files/GABM_V...
(w/ @wanlo.bsky.social @mstrohm.bsky.social and @janalasser.bsky.social)
I'll present a related working paper on validating LLM social simulations at the ABM session on Tuesday (11 AM, Vingen 7): indiiigo.github.io/files/GABM_V...
(w/ @wanlo.bsky.social @mstrohm.bsky.social and @janalasser.bsky.social)
Reposted by Georg Ahnert
Do LLMs represent the people they're supposed simulate or provide personalized assistance to?
We review the current literature in our #ACL2025 Findings paper and investigating what researchers conclude about the demographic representativeness of LLMs:
osf.io/preprints/so...
1/
We review the current literature in our #ACL2025 Findings paper and investigating what researchers conclude about the demographic representativeness of LLMs:
osf.io/preprints/so...
1/
July 21, 2025 at 10:12 AM
Do LLMs represent the people they're supposed simulate or provide personalized assistance to?
We review the current literature in our #ACL2025 Findings paper and investigating what researchers conclude about the demographic representativeness of LLMs:
osf.io/preprints/so...
1/
We review the current literature in our #ACL2025 Findings paper and investigating what researchers conclude about the demographic representativeness of LLMs:
osf.io/preprints/so...
1/
Reposted by Georg Ahnert
LLMs can understand political discourse, but can they actually predict votes of real politicians?
Excited to share my work at #IC2S2 this week!
I will present my poster on Tuesday between 1:30 and 3:30 p.m.
Excited to share my work at #IC2S2 this week!
I will present my poster on Tuesday between 1:30 and 3:30 p.m.
July 21, 2025 at 10:37 AM
LLMs can understand political discourse, but can they actually predict votes of real politicians?
Excited to share my work at #IC2S2 this week!
I will present my poster on Tuesday between 1:30 and 3:30 p.m.
Excited to share my work at #IC2S2 this week!
I will present my poster on Tuesday between 1:30 and 3:30 p.m.
Really excited to also present this work at #IC2S2 next week in Norrköping! 🎉 I'd love to discuss how to produce LLM survey responses at my poster on Wed at 13:30 (Poster Session 2, Poster ID 68) 📊
LLMs are trained to produce open-ended responses 📝, but most survey items require closed-ended responses instead 📊
This Wed 11:00–12:30 at #ESRA25, I'll discuss the large impact that Answer Production Methods have on prediction results + share recommendations for methods and parameters. 👈
This Wed 11:00–12:30 at #ESRA25, I'll discuss the large impact that Answer Production Methods have on prediction results + share recommendations for methods and parameters. 👈
July 18, 2025 at 3:19 PM
Really excited to also present this work at #IC2S2 next week in Norrköping! 🎉 I'd love to discuss how to produce LLM survey responses at my poster on Wed at 13:30 (Poster Session 2, Poster ID 68) 📊
Reposted by Georg Ahnert
LLMs can generate synthetic survey responses, e.g. for imputation, but how reliable are they? 📋
At #IC2S2, I'll be sharing our research on the robustness of AI-generated responses to perturbations and if they mirror human survey biases. 🤖
Come by my poster on Tuesday between 1:30 and 3:30 p.m.
At #IC2S2, I'll be sharing our research on the robustness of AI-generated responses to perturbations and if they mirror human survey biases. 🤖
Come by my poster on Tuesday between 1:30 and 3:30 p.m.
July 18, 2025 at 2:16 PM
LLMs can generate synthetic survey responses, e.g. for imputation, but how reliable are they? 📋
At #IC2S2, I'll be sharing our research on the robustness of AI-generated responses to perturbations and if they mirror human survey biases. 🤖
Come by my poster on Tuesday between 1:30 and 3:30 p.m.
At #IC2S2, I'll be sharing our research on the robustness of AI-generated responses to perturbations and if they mirror human survey biases. 🤖
Come by my poster on Tuesday between 1:30 and 3:30 p.m.
Reposted by Georg Ahnert
Very excited to head to #IC2S2 next week! 🎉
In our project, we tested whether a psychological assessment can measure sexism in LLMs, and found that applying such tools to LLMs is not as straightforward as it seems.
Find me and my poster at Poster Session 1 (Tue 12:30-14:30) — hope to see you there
In our project, we tested whether a psychological assessment can measure sexism in LLMs, and found that applying such tools to LLMs is not as straightforward as it seems.
Find me and my poster at Poster Session 1 (Tue 12:30-14:30) — hope to see you there
July 17, 2025 at 7:14 PM
Very excited to head to #IC2S2 next week! 🎉
In our project, we tested whether a psychological assessment can measure sexism in LLMs, and found that applying such tools to LLMs is not as straightforward as it seems.
Find me and my poster at Poster Session 1 (Tue 12:30-14:30) — hope to see you there
In our project, we tested whether a psychological assessment can measure sexism in LLMs, and found that applying such tools to LLMs is not as straightforward as it seems.
Find me and my poster at Poster Session 1 (Tue 12:30-14:30) — hope to see you there
LLMs are trained to produce open-ended responses 📝, but most survey items require closed-ended responses instead 📊
This Wed 11:00–12:30 at #ESRA25, I'll discuss the large impact that Answer Production Methods have on prediction results + share recommendations for methods and parameters. 👈
This Wed 11:00–12:30 at #ESRA25, I'll discuss the large impact that Answer Production Methods have on prediction results + share recommendations for methods and parameters. 👈
July 14, 2025 at 1:34 PM
LLMs are trained to produce open-ended responses 📝, but most survey items require closed-ended responses instead 📊
This Wed 11:00–12:30 at #ESRA25, I'll discuss the large impact that Answer Production Methods have on prediction results + share recommendations for methods and parameters. 👈
This Wed 11:00–12:30 at #ESRA25, I'll discuss the large impact that Answer Production Methods have on prediction results + share recommendations for methods and parameters. 👈
Excited to present our paper with @maxpe.bsky.social, @dgarcia.eu, and @mstrohm.bsky.social next week at #ICWSM! ✨
We extend social simulation with LLMs to a longitudinal setting by fine-tuning Temporal Adapters—here's how: 🧵
We extend social simulation with LLMs to a longitudinal setting by fine-tuning Temporal Adapters—here's how: 🧵
June 16, 2025 at 8:23 AM
Excited to present our paper with @maxpe.bsky.social, @dgarcia.eu, and @mstrohm.bsky.social next week at #ICWSM! ✨
We extend social simulation with LLMs to a longitudinal setting by fine-tuning Temporal Adapters—here's how: 🧵
We extend social simulation with LLMs to a longitudinal setting by fine-tuning Temporal Adapters—here's how: 🧵
Reposted by Georg Ahnert
We're excited to announce #DataFest Germany 2025 at LMU Munich, March 28-30! In this #hackathon, students from diverse study programs compete for the best insights and visualizations from an exclusive dataset within 48 hours. More info: www.datafest.de/home
DataFest 🇩🇪 2025
Call for applications 2025! 📢
We are glad to announce our call for applications to join the 8th edition of DataFest Germany, which will take place at the Ludwig-Maximilians-Universität in Munich (Marc...
www.datafest.de
January 31, 2025 at 9:43 AM
We're excited to announce #DataFest Germany 2025 at LMU Munich, March 28-30! In this #hackathon, students from diverse study programs compete for the best insights and visualizations from an exclusive dataset within 48 hours. More info: www.datafest.de/home
Reposted by Georg Ahnert
Ready for another Computational Social Science Starter Pack?
Here is number 2! More amazing folks to follow! Many students and the next gen represented!
go.bsky.app/GoEyD7d
Here is number 2! More amazing folks to follow! Many students and the next gen represented!
go.bsky.app/GoEyD7d
November 14, 2024 at 11:42 PM
Ready for another Computational Social Science Starter Pack?
Here is number 2! More amazing folks to follow! Many students and the next gen represented!
go.bsky.app/GoEyD7d
Here is number 2! More amazing folks to follow! Many students and the next gen represented!
go.bsky.app/GoEyD7d
Reposted by Georg Ahnert
Sharing my first Computational Social Science starter pack! Will grow with time, feel free to nominate and self nominate!
go.bsky.app/CYmRvcK
go.bsky.app/CYmRvcK
November 13, 2024 at 2:05 AM
Sharing my first Computational Social Science starter pack! Will grow with time, feel free to nominate and self nominate!
go.bsky.app/CYmRvcK
go.bsky.app/CYmRvcK
Reposted by Georg Ahnert
Repost if you’ve participated in a Summer Institute in Computational Social Science. Let’s get #SICSS Bluesky going!
October 8, 2023 at 7:49 PM
Repost if you’ve participated in a Summer Institute in Computational Social Science. Let’s get #SICSS Bluesky going!