Professor at LMU Munich | Institute of AI in Management ++ We develop artificial intelligence for impact ++
https://www.som.lmu.de/ai/en/index.html
Stefan Feuerriegel
Loading...
🎉 New preprint: Can #LLMs automate reproducibility checks?
👉We test this on 76 social & behavioral studies
✅Our LLM pipeline arrived at original qualitative conclusions in 96% of cases
🎯We recovered the effect sizes in 41% (human reanalysts: 34%)
arxiv.org/abs/2606.13670
Stefan Feuerriegel
⚽️Introducing 𝐋𝐋𝐌 𝐒𝐨𝐜𝐜𝐞𝐫𝐀𝐫𝐞𝐧𝐚: a benchmarking platform for real-world LLM predictions
✅Predictions for 104 games @FIFAWorldCup with frontier LLMs
🏆Opus 4.8: Spain / GPT-5.5: Spain / Grok 4.3: Argentina / Mistral-large: France
➡️All predictions & leaderboard llmsoccerarena.up.railway.app
📣 New paper @nathumbehav.nature.com: A reporting checklist for large language models in behavioural science
www.nature.com/articles/s41...
@cbarrie.bsky.social @killianmcloughlin.bsky.social @danmirea.bsky.social @diyiyang.bsky.social @mariaa.bsky.social @umangsbhatt.bsky.social @angelhwang.bsky.social @bmittelstadt.bsky.social @informor.bsky.social @desmond-ong.bsky.social @frapierri.bsky.social
and many more!
🎉New preprint: #CausalML to analyze effects of behavioral interventions
• We use #CausalML to learn when loss vs. gain framing works
• 2 field experiments (N=41,207) from retirement saving
• Personalization⬆️participation +51% & savings +18%
papers.ssrn.com/sol3/papers....
Stefan Feuerriegel
🏥💊New paper on #CausalML in #oncology:
Treatment effect heterogeneity of radiotherapy in localized Ewing sarcoma: A secondary analysis of the EURO-E.W.I.N.G. 99 and Ewing 2008 trial
📄 doi.org/10.1016/j.ej...
Happy to have provided my tiny contribution to this!
Stefan Feuerriegel
Stefan Feuerriegel
Stefan Feuerriegel
Stefan Feuerriegel
LLMs are used widely in the behavioral sciences. But we have no good standards for how to do so.
We introduce a consensus-based reporting checklist to improve transparency, reproducibility and ethical accountability of LLM-based research in the behavioural sciences.
www.nature.com/articles/s41...
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...
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...
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...
📣 Reporting checklist for LLMs in behavioral and social science
New article presenting a consensus-based reporting checklist (GUIDE-LLM) for the use of LLMs in the behavioral and social sciences to foster transparency, reproducibility, and ethical use.
🔗 www.nature.com/articles/s41...
