activity
20232026
most citedCan Unconfident LLM Annotations Be Used for Confident Conclusions?

3 citations · 5 across the 8 of their papers we have counts for

collaborators

10 papers

cs.CL2026

Mitigating LLM-based p-Hacking by Preregistering for the Next LLM

Maria Thomas, Kristina Gligoric, Nihar B. Shah

Large language models (LLMs) are increasingly used to generate, classify, and annotate data whose outputs feed downstream hypothesis tests. However, LLM-based research is easy to p…

cs.CR2026

Cooking Up Risks: Benchmarking and Reducing Food Safety Risks in Large Language Models

Weidi Luo, Xiaofei Wen, Tenghao Huang +5

Large language models (LLMs) are increasingly deployed for everyday tasks, including food preparation and health-related guidance. However, food safety remains a high-stakes domain…

cs.CL2026

SWAY: A Counterfactual Computational Linguistic Approach to Measuring and Mitigating Sycophancy

Joy Bhalla, Kristina Gligorić

Large language models exhibit sycophancy: the tendency to shift outputs toward user-expressed stances, regardless of correctness or consistency. While prior work has studied this i…

cs.CL2026

Multi-Perspective LLM Annotations for Valid Analyses in Subjective Tasks

Navya Mehrotra, Adam Visokay, Kristina Gligorić

Large language models are increasingly used to annotate texts, but their outputs reflect some human perspectives better than others. Existing methods for correcting LLM annotation…

cs.CL2025

Valid Survey Simulations with Limited Human Data: The Roles of Prompting, Fine-Tuning, and Rectification

Stefan Krsteski, Giuseppe Russo, Serina Chang +2

Surveys provide valuable insights into public opinion and behavior, but their execution is costly and slow. Large language models (LLMs) have been proposed as a scalable, low-cost…

cs.CY2025

Attention to Non-Adopters

Kaitlyn Zhou, Kristina Gligorić, Myra Cheng +7

Although language model-based chat systems are increasingly used in daily life, most Americans remain non-adopters of chat-based LLMs -- as of June 2025, 66% had never used ChatGPT…