Stephanie Lin

AI researcher; lead author of TruthfulQA; previously a research scholar at Oxford and resident at OpenAI.

Role: researcher
Currently at: OpenAI
Twitter: twitter.com/sylinrl
GitHub: github.com/sylinrl
Scholar: openreview.net/profile
Papers: 4

Cite

Notes

Only stored in your browser.

Attribution

Affiliations & profile: openreview.net/profile

Attribution policy →

4papers·1eval contribs

Authored papers

GPT-4 Technical Report

gpt-4-technical-report

2023

Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models

TMLR

2022

Teaching Models to Express Their Uncertainty in Words

arXiv 2022

2022

TruthfulQA: Measuring How Models Mimic Human Falsehoods

ACL

2021

Eval contributions

TruthfulQA

Future of Humanity Institute (Oxford)

817 questions targeting common human misconceptions, measuring whether a model gives factually true answers or repeats popular falsehoods.

SaturatedHallucinationFactual Recall

Affiliations

Currently at

OpenAI

researcher · frontier lab

Previously

University of Oxforduniversity lab

Frequent co-authors

from 4 papers

Jacob Hilton

researcher

3 shared papers

Owain Evans

founder

3 shared papers

Alethea Power

researcher

2 shared papers

Angela Jiang

2 shared papers

Barret Zoph

founder

2 shared papers

Daniel Levy

2 shared papers

David Dohan

researcher

2 shared papers

Derek Chen

2 shared papers

Giambattista Parascandolo

2 shared papers

Jason Wei

research-scientist

2 shared papers