banner
wanlo.bsky.social
Georg Ahnert
@wanlo.bsky.social
190 followers 390 following 14 posts
PhD Student in Social Data Science at University of Mannheim | LLMs and Surveys | georgahnert.de
Posts Media Videos Starter Packs
Pinned
wanlo.bsky.social
Georg Ahnert @wanlo.bsky.social · Jul 18
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) 📊
wanlo.bsky.social
Georg Ahnert @wanlo.bsky.social · Jul 14
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. 👈
A research setup for the evaluation of Answer Production Methods for closed-ended survey responses from LLMs. An LLM is prompted with a survey and an optional instruction, before a Answer Production Method is applied. These methods range from token-probabilities to open-ended text generation + classification. I then evaluated them against human survey answers and calculate individual-level accuracy as well as distribution alignment for sub-populations.
6 18
Reposted by Georg Ahnert
indiiigo.bsky.social
Indira Sen @indiiigo.bsky.social · Jul 29
👋 #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!
7 22
Reposted by Georg Ahnert
ic2s2.bsky.social
International Conference on Computational Social Science @ic2s2.bsky.social · Jul 25
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
1 19 43
wanlo.bsky.social
Georg Ahnert @wanlo.bsky.social · Jul 24
Here‘s some of the slides 👇 bsky.app/profile/mstr...
mstrohm.bsky.social
Markus Strohmaier @mstrohm.bsky.social · Jul 22
opening slides #ic2s2
1
Reposted by Georg Ahnert
mstrohm.bsky.social
Markus Strohmaier @mstrohm.bsky.social · Jul 23
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
4 21
wanlo.bsky.social
Georg Ahnert @wanlo.bsky.social · Jul 23
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!
Laura Nelson on stage presenting her keynote at IC2S2. The slide lays out "A maturing field" of Computational Qualitative Research
12
Reposted by Georg Ahnert
indiiigo.bsky.social
Indira Sen @indiiigo.bsky.social · Jul 21
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)
6 17
Reposted by Georg Ahnert
indiiigo.bsky.social
Indira Sen @indiiigo.bsky.social · Jul 21
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/
Screenshot of our paper "Missing the Margins: A Systematic Literature Review on the Demographic Representativeness of LLMs" Details about what we annotated in our systematic review
2 8 23
Reposted by Georg Ahnert
maximiliankreutner.bsky.social
Maximilian Kreutner @maximiliankreutner.bsky.social · Jul 21
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.
2 5
wanlo.bsky.social
Georg Ahnert @wanlo.bsky.social · Jul 20
The 15.07 train has a 30 min delay now but the landscape‘s quite pretty ;)
The Swedish countryside as seen from a moving train, with a lake, a red and white house, and some cows.
1
wanlo.bsky.social
Georg Ahnert @wanlo.bsky.social · Jul 18
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) 📊
wanlo.bsky.social
Georg Ahnert @wanlo.bsky.social · Jul 14
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. 👈
A research setup for the evaluation of Answer Production Methods for closed-ended survey responses from LLMs. An LLM is prompted with a survey and an optional instruction, before a Answer Production Method is applied. These methods range from token-probabilities to open-ended text generation + classification. I then evaluated them against human survey answers and calculate individual-level accuracy as well as distribution alignment for sub-populations.
6 18
Reposted by Georg Ahnert
jrupprec.bsky.social
Jens Rupprecht @jrupprec.bsky.social · Jul 18
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.
3 7
Reposted by Georg Ahnert
janajung.bsky.social
Jana Jung @janajung.bsky.social · Jul 17
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
4 9
wanlo.bsky.social
Georg Ahnert @wanlo.bsky.social · Jul 14
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. 👈
A research setup for the evaluation of Answer Production Methods for closed-ended survey responses from LLMs. An LLM is prompted with a survey and an optional instruction, before a Answer Production Method is applied. These methods range from token-probabilities to open-ended text generation + classification. I then evaluated them against human survey answers and calculate individual-level accuracy as well as distribution alignment for sub-populations.
4 10
wanlo.bsky.social
Georg Ahnert @wanlo.bsky.social · Jun 27
Thanks :) We have a BERT-based baseline model that labels individual tweets—but I agree, would be a very interesting comparison now that LLMs can increasingly handle super long contexts!
1
Reposted by Georg Ahnert
icwsm.bsky.social
icwsm.bsky.social @icwsm.bsky.social · Jun 26
Day 3 morning sessions: language change and generative AI #ICWSM
1 8
wanlo.bsky.social
Georg Ahnert @wanlo.bsky.social · Jun 16
Thanks a lot for the shoutout! Would be happy to talk about this and other ongoing projects on social simulation at #ICWSM next week 🙂
wanlo.bsky.social
Georg Ahnert @wanlo.bsky.social · Jun 16
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: 🧵
A lineplot that shows how scared people in the UK were over time, during the first COVID-19 lockdown. Our method (Llama 3 Temporal Adapters) produces similar estimates of as the survey data gathered by YouGov.
wanlo.bsky.social
Georg Ahnert @wanlo.bsky.social · Jun 16
Our conclusion: Temporal Adapters enable longitudinal analyses of affect aggregates from social media data by temporally aligning LLMs. ⏱️

Read the full paper: ojs.aaai.org/index.php/IC...
Extracting Affect Aggregates from Longitudinal Social Media Data with Temporal Adapters for Large Language Models | Proceedings of the International AAAI Conference on Web and Social Media ...
ojs.aaai.org
wanlo.bsky.social
Georg Ahnert @wanlo.bsky.social · Jun 16
Results: From several collective emotions and public opinion, our longitudinal estimates show a strong positive and significant cross-correlation with survey data gathered by YouGov directly from human participants.
Our estimates with Llama 3 Temporal Adapters show a strong positive and significant correlation with collective frustration, fear, boredom, and sadness. Our results vary strongly between emotions, but they are in line with a baseline method's estimates. We also apply our method to the extraction of public attitudes towards Boris Johnson as a prime minister and towards the National Healthy Service, were we similarly find positive cross-correlation with survey data for some but not all answer options.
1
wanlo.bsky.social
Georg Ahnert @wanlo.bsky.social · Jun 16
Method: We gather weekly text data from a panel of Twitter users and fine-tune Temporal Adapters for Llama 3 8B with it. 🦙 We then prompt Llama with established survey questions, one week at a time, to extract longitudinal affect aggregates.
Overview of our method that shows how each week's Twitter data is used to train a separate Temporal Adapter, and how a weekly affect aggregate is then obtained from the LLM's token probabilities.
1
wanlo.bsky.social
Georg Ahnert @wanlo.bsky.social · Jun 16
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: 🧵
A lineplot that shows how scared people in the UK were over time, during the first COVID-19 lockdown. Our method (Llama 3 Temporal Adapters) produces similar estimates of as the survey data gathered by YouGov.
1 5 16
Reposted by Georg Ahnert
datafestgermany.bsky.social
DataFest Germany @datafestgermany.bsky.social · Jan 31
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
5 9
wanlo.bsky.social
Georg Ahnert @wanlo.bsky.social · Dec 19
Great to see such strong arguments for using "open-weight" LLMs! Maybe setting random seeds could be added to the advice to practitioners? Most interfaces seem to support this now—huggingface, OpenAI, Ollama, vllm,…
2
Reposted by Georg Ahnert
emilioferrara.bsky.social
Emilio Ferrara @emilioferrara.bsky.social · Nov 14
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
33 53 77
Reposted by Georg Ahnert
emilioferrara.bsky.social
Emilio Ferrara @emilioferrara.bsky.social · Nov 13
Sharing my first Computational Social Science starter pack! Will grow with time, feel free to nominate and self nominate!

go.bsky.app/CYmRvcK
61 41 97
Reposted by Georg Ahnert
chrisbail.bsky.social
Chris Bail @chrisbail.bsky.social · Oct 8
Repost if you’ve participated in a Summer Institute in Computational Social Science. Let’s get #SICSS Bluesky going!
63 51