Rafal Kocielnik PRO

RKocielnik

·

http://www.rkocielnik.com

AI & ML interests

Social Bias in AI, Few-shot Learning, Deep Language Models, Human-Computer Interaction

Organizations

authored 3 papers 3 months ago

The Personality Illusion: Revealing Dissociation Between Self-Reports & Behavior in LLMs

Paper • 2509.03730 • Published Sep 3, 2025 • 3

Rethinking Psychometric Evaluation of LLMs: When and Why Self-Reports Predict Behavior

Paper • 2606.12730 • Published Jun 10 • 7

On the Limits of LLM Adaptability: Impact of Model-Internalized Priors on Annotation Task Performance

Paper • 2606.00467 • Published May 30 • 1

submitted 2 papers to Daily Papers 3 months ago

On the Limits of LLM Adaptability: Impact of Model-Internalized Priors on Annotation Task Performance

Paper • 2606.00467 • Published May 30 • 1

Rethinking Psychometric Evaluation of LLMs: When and Why Self-Reports Predict Behavior

Paper • 2606.12730 • Published Jun 10 • 7

authored a paper over 1 year ago

Automating Feedback Analysis in Surgical Training: Detection, Categorization, and Assessment

Paper • 2412.00760 • Published Dec 1, 2024

authored 5 papers over 2 years ago

Can You Label Less by Using Out-of-Domain Data? Active & Transfer Learning with Few-shot Instructions

Paper • 2211.11798 • Published Nov 21, 2022

Deep Multimodal Fusion for Surgical Feedback Classification

Paper • 2312.03231 • Published Dec 6, 2023

BiasTestGPT: Using ChatGPT for Social Bias Testing of Language Models

Paper • 2302.07371 • Published Feb 14, 2023

Exploring Social Bias in Downstream Applications of Text-to-Image Foundation Models

Paper • 2312.10065 • Published Dec 5, 2023

Few-shot Instruction Prompts for Pretrained Language Models to Detect Social Biases

Paper • 2112.07868 • Published Dec 15, 2021