Agora | Research Hub

Citations & Impact

All-time

Citations

4,999

H-index

26

i10-index

32

Publications

20

Co-authors

14

list available

Contact

Emailyanaiela@gmail.com TwitterOpen ↗GitHubOpen ↗

Publications

8 items

Rewriting History: A Recipe for Interventional Analyses to Study Data Effects on Model Behavior

2025

Cited

0

On Linear Representations and Pretraining Data Frequency in Language Models

2025

Cited

0

OLMoTrace: Tracing Language Model Outputs Back to Trillions of Training Tokens

2025

Cited

0

Better Aligned with Survey Respondents or Training Data? Unveiling Political Leanings of LLMs on U.S. Supreme Court Cases

2025

Cited

0

GRADE: Quantifying Sample Diversity in Text-to-Image Models

arXiv.org · 2024

Cited

0

Hybrid Preferences: Learning to Route Instances for Human vs. AI Feedback

arXiv.org · 2024

Cited

2

Generalization v.s. Memorization: Tracing Language Models' Capabilities Back to Pretraining Data

arXiv.org · 2024

Cited

16

Evaluating n-Gram Novelty of Language Models Using Rusty-DAWG

Conference on Empirical Methods in Natural Language Processing · 2024

Cited

14

Resume (English only)

Academic Achievements

OLMoTrace received Best Demo Award at ACL 2025
OLMo and Dolma received Best Paper Awards at ACL 2024
Paper 'What's In My Big Data?' selected as ICLR 2024 Spotlight
Co-organized the 1st Data Contamination Workshop at ACL 2024
Keynote speaker at The First Workshop on Large Language Model Memorization (L2M2) @ ACL 2025
Invited talk at RIKEN, Tokyo
Interviewed by Science News
Interviewed on the Causal Bandits podcast
Served as meta-reviewer for ACL-ARR (EMNLP)

Co-authors

14 total