no code implementations • 7 Mar 2024 • Savvas Petridis, Ben Wedin, Ann Yuan, James Wexler, Nithum Thain
We also show that we can improve overall performance by learning unique prompts for different semantic regions of the training data and using a mixture-of-experts (MoE) architecture to route inputs at inference time.
no code implementations • 24 Oct 2023 • Savvas Petridis, Michael Terry, Carrie J. Cai
Prototyping AI applications is notoriously difficult.
no code implementations • 24 Oct 2023 • Savvas Petridis, Ben Wedin, James Wexler, Aaron Donsbach, Mahima Pushkarna, Nitesh Goyal, Carrie J. Cai, Michael Terry
Inspired by these findings, we developed ConstitutionMaker, an interactive tool for converting user feedback into principles, to steer LLM-based chatbots.
1 code implementation • 19 May 2023 • Emily Reif, Minsuk Kahng, Savvas Petridis
We present LinguisticLens, a novel inter-active visualization tool for making sense of and analyzing syntactic diversity of LLM-generated datasets.
no code implementations • 22 Oct 2021 • Katy Ilonka Gero, Chris Kedzie, Savvas Petridis, Lydia Chilton
Language models are known to produce vague and generic outputs.
2 code implementations • WS 2018 • Tariq Alhindi, Savvas Petridis, Smar Muresan, a
Fact-checking is a journalistic practice that compares a claim made publicly against trusted sources of facts.