5 papers
On the Limits of LLM Adaptability: Impact of Model-Internalized Priors on Annotation Task Performance
Etienne Casanova, Rafal Kocielnik, R. Michael Alvarez
Large Language Models (LLMs) are increasingly used for zero-shot annotation and LLM-as-a-judge tasks, yet their reliability hinges on how model-internalized priors interact with us…
Automating Feedback Analysis in Surgical Training: Detection, Categorization, and Assessment
Firdavs Nasriddinov, Rafal Kocielnik, Arushi Gupta +4
This work introduces the first framework for reconstructing surgical dialogue from unstructured real-world recordings, which is crucial for characterizing teaching tasks. In surgic…
Multi-Modal Self-Supervised Learning for Surgical Feedback Effectiveness Assessment
Arushi Gupta, Rafal Kocielnik, Jiayun Wang +5
During surgical training, real-time feedback from trainers to trainees is important for preventing errors and enhancing long-term skill acquisition. Accurately predicting the effec…
Online Moderation in Competitive Action Games: How Intervention Affects Player Behaviors
Zhuofang Li, Rafal Kocielnik, Mitchell Linegar +7
Online competitive action games have flourished as a space for entertainment and social connections, yet they face challenges from a small percentage of players engaging in disrupt…
ChatGPT Based Data Augmentation for Improved Parameter-Efficient Debiasing of LLMs
Pengrui Han, Rafal Kocielnik, Adhithya Saravanan +3
Large Language models (LLMs), while powerful, exhibit harmful social biases. Debiasing is often challenging due to computational costs, data constraints, and potential degradation…