4 papers
Form Over Content In Gradient-Based Data Attribution Methods
Sunwoo Kim, Seokwon Jung, Sohyung Kim +2
Data attribution methods using gradient similarity are widely used to analyze and select training data for large language models, but what gradient similarity actually measures is…
The Role of Fine-grained Harm Signals in LLM Safety
Soyeon Park, Seogyeong Jeong, Sunwoo Kim +1
Prior work has shown that internal harmfulness representations in large language models vary across risk categories, while sharing a common general harm representation component. T…
On the Effect of Uncertainty on Layer-wise Inference Dynamics
Sunwoo Kim, Haneul Yoo, Alice Oh
Understanding how large language models (LLMs) internally represent and process their predictions is central to detecting uncertainty and preventing hallucinations. While several s…
PapersPlease: A Benchmark for Evaluating Motivational Values of Large Language Models Based on ERG Theory
Junho Myung, Yeon Su Park, Sunwoo Kim +2
Evaluating the performance and biases of large language models (LLMs) through role-playing scenarios is becoming increasingly common, as LLMs often exhibit biased behaviors in thes…