Trusted Source Alignment in Large Language Models

no code implementations • 12 Nov 2023 • Vasilisa Bashlovkina, Zhaobin Kuang, Riley Matthews, Edward Clifford, Yennie Jun, William W. Cohen, Simon Baumgartner

Large language models (LLMs) are trained on web-scale corpora that inevitably include contradictory factual information from sources of varying reliability.

Fact Checking

SMILE: Evaluation and Domain Adaptation for Social Media Language Understanding

no code implementations • 30 Jun 2023 • Vasilisa Bashlovkina, Riley Matthews, Zhaobin Kuang, Simon Baumgartner, Michael Bendersky

We study the ability of transformer-based language models (LMs) to understand social media language.

Domain Adaptation