3 citations · 5 across the 8 of their papers we have counts for
6 papers · 1 filter
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…
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…
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…
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…
Can Unconfident LLM Annotations Be Used for Confident Conclusions?
Kristina Gligorić, Tijana Zrnic, Cinoo Lee +2
Large language models (LLMs) have shown high agreement with human raters across a variety of tasks, demonstrating potential to ease the challenges of human data collection. In comp…
Grounding Gaps in Language Model Generations
Omar Shaikh, Kristina Gligorić, Ashna Khetan +3
Effective conversation requires common ground: a shared understanding between the participants. Common ground, however, does not emerge spontaneously in conversation. Speakers and…