activity
20232026
most citedHumanity's Last Exam

23 citations · 48 across the 7 of their papers we have counts for

collaborators
Showing cs.CLShow all

6 papers · 1 filter

cs.CL2026

Characterizing Cultural Localization in AI-Generated Stories

Shaily Bhatt, Supriti Vijay, Jeremiah Milbauer +1

The global use of artificial intelligence has increased interest in assessing the ability to generate culturally localized content, including stories. Cultural localization in stor…

cs.CL2025

Beyond Text: Characterizing Domain Expert Needs in Document Research

Sireesh Gururaja, Nupoor Gandhi, Jeremiah Milbauer +1

Working with documents is a key part of almost any knowledge work, from contextualizing research in a literature review to reviewing legal precedent. Recently, as their capabilitie…

cs.CL20242 cited

Stereotype or Personalization? User Identity Biases Chatbot Recommendations

Anjali Kantharuban, Jeremiah Milbauer, Maarten Sap +2

While personalized recommendations are often desired by users, it can be difficult in practice to distinguish cases of bias from cases of personalization: we find that models gener…

cs.CL2023

From Nuisance to News Sense: Augmenting the News with Cross-Document Evidence and Context

Jeremiah Milbauer, Ziqi Ding, Zhijin Wu +1

Reading and understanding the stories in the news is increasingly difficult. Reporting on stories evolves rapidly, politicized news venues offer different perspectives (and sometim…

cs.CL2023

LLMs as Workers in Human-Computational Algorithms? Replicating Crowdsourcing Pipelines with LLMs

Tongshuang Wu, Haiyi Zhu, Maya Albayrak +21

LLMs have shown promise in replicating human-like behavior in crowdsourcing tasks that were previously thought to be exclusive to human abilities. However, current efforts focus ma…

cs.CL2023

LAIT: Efficient Multi-Segment Encoding in Transformers with Layer-Adjustable Interaction

Jeremiah Milbauer, Annie Louis, Mohammad Javad Hosseini +3

Transformer encoders contextualize token representations by attending to all other tokens at each layer, leading to quadratic increase in compute effort with the input length. In p…