Elamur Research⌕
☰
home / authors / Nancy Fulda

Nancy Fulda

Nancy Fulda has 2 papers in our library, in 2022, most of them on Language models & pretraining; often with Christopher Michael Rytting, David Wingate, Joshua Robinson.

2 papers in our library · 2022

OpenAlex · ORCID · Wikidata · h-index 11 · 53 works · 1,163 citations OpenAlex, 2026-10-14

📄 2 works in our library · 🔗 278 citations in our library · 1 more in our library without a page yet · ⭐ Paper Star rank #2024

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology

 Affiliations

🎓Brigham Young UniversityProvo · United States2003–2026 · 39 paperscurrent

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine.

 Concepts, shelves and topics

Of its works in our library: the number of works on each and its rating among them.

📚 Shelves 10 Arts and Humanities · 2 works Language and Linguistics · 2 works Physics and Astronomy · 1 work Social Sciences · 1 work General Social Sciences · 1 work Safety Research · 1 work Statistical and Nonlinear Physics · 1 work Computer Science · 1 work Artificial Intelligence · 1 work Information Systems · 1 work

🧭 Topics 1 Language models & pretraining · 1 work

 Works by year

2020s

20222 papers

 Papers

The most cited first (OpenAlex and our library).

  1. Out of One, Many: Using Language Models to Simulate Human Samples (2022 · 944 citations)
    Social scientists usually treat bias in large language models as one flaw to remove. Argyle and colleagues argue that GPT-3 holds many group-specific biases, and that these can be used on purpose. If you condition the model on a detailed demographic profile, it should answer the way people with that background tend…
  2. 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.

All works

3 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

  1. Out of One, Many: Using Language Models to Simulate Human SamplesLisa P. Argyle, Ethan C. Busby, Nancy Fulda, et al.arXiv:2209.06899 · 944 citations
  2. An Information-theoretic Approach to Prompt Engineering Without Ground Truth LabelsTaylor Sorensen, Joshua Robinson, Christopher Rytting, et al.Annual Meeting of the Association for… · 178 citations
  3. Can Humor Prediction Datasets be used for Humor Generation? Humorous Headline Generation via Style Transfer (original ↗)Orion Weller, Nancy Fulda, Kevin Seppi2020 · Proceedings of the Second Workshop on… · 23 citations · no summary yet

 Co-authors here

5 co-authors with a page, the most papers together first.

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

 Cited by

Papers of our library cite their works 278 times (of the 141,840 papers whose bibliographies we read); 22 citing papers with a page here →.

Updated

This page in Markdown → https://md.research.elamur.ai/free/en/authors/nancy-fulda/