André Cruz
@andcrz.bsky.social
🎓 PhD student at the Max Planck Institute for Intelligent Systems
🔬 Safe and robust AI, algorithms and society
🔗 https://andrefcruz.github.io
📍 researcher in 🇩🇪, from 🇵🇹
🔬 Safe and robust AI, algorithms and society
🔗 https://andrefcruz.github.io
📍 researcher in 🇩🇪, from 🇵🇹
The paper is accompanied by a new benchmark package: *Folktexts*. It builds socio-demographic backstories from Census data to evaluate LLM calibration, fairness, and uncertainty estimation.
Package: github.com/socialfounda...
Paper: arxiv.org/pdf/2407.14614
Package: github.com/socialfounda...
Paper: arxiv.org/pdf/2407.14614
GitHub - socialfoundations/folktexts: Evaluate uncertainty, calibration, accuracy, and fairness of LLMs on real-world survey data!
Evaluate uncertainty, calibration, accuracy, and fairness of LLMs on real-world survey data! - socialfoundations/folktexts
github.com
February 6, 2025 at 11:10 PM
The paper is accompanied by a new benchmark package: *Folktexts*. It builds socio-demographic backstories from Census data to evaluate LLM calibration, fairness, and uncertainty estimation.
Package: github.com/socialfounda...
Paper: arxiv.org/pdf/2407.14614
Package: github.com/socialfounda...
Paper: arxiv.org/pdf/2407.14614