Joshua Robinson
Joshua Robinson has 2 papers in our library, in 2022, most of them on Language models & pretraining, Question answering; often with Christopher Michael Rytting, David Wingate, Mahmoud Khalil.
OpenAlex · ORCID · Wikidata · h-index 65 · 398 works · 20,482 citations OpenAlex, 2026-10-14
📄 2 works in our library · 🔗 Cited 189 times in our library · ⭐ Paper Stars ranking: #4041
Affiliations
Concepts, shelves and topics
📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Arts and Humanities · 2 worksComputer Science · 2 worksArtificial Intelligence · 2 worksLanguage and Linguistics · 2 worksInformation Systems · 1 workComputer Vision and Pattern Recognition · 1 work
🧭 Topics 2Research subjects and languages the work is about.Language models & pretraining · 1 workQuestion answering · 1 work
Works by year
2020s
Papers
- An Information-theoretic Approach to Prompt Engineering Without Ground Truth Labels (2022 · 178 citations)
Large language models are highly sensitive to how a prompt is worded. Picking a good template usually requires a labeled validation set, or gradient access to the model for continuous prompt tuning. Sorensen et al. propose a label-free alternative that needs only the model's output probabilities. - Leveraging Large Language Models for Multiple Choice Question Answering (2022 · 157 citations)
Large language models such as GPT-3 do well on multiple choice question answering (MCQA) in zero-, one-, and few-shot settings, yet still trail specialized state-of-the-art (SOTA) systems.
Co-authors here
Venues
Cited by
Updated
This page in Markdown → https://md.research.elamur.ai/free/en/authors/joshua-robinson/