3 papers
cs.AI2026
In-Context Examples Suppress Scientific Knowledge Recall in LLMs
Chaemin Jang, Woojin Park, Hyeok Yun +2
Scientific reasoning rarely stops at what is directly observable; it often requires uncovering hidden structure from data. From estimating reaction constants in chemistry to inferr…
cs.AI2026
Ideological Bias in LLMs' Economic Causal Reasoning
Donggyu Lee, Hyeok Yun, Jungwon Kim +4
Do large language models (LLMs) exhibit systematic ideological bias when reasoning about economic causal effects? As LLMs are increasingly used in policy analysis and economic repo…
cs.LG2025
Adaptive Task Vectors for Large Language Models
Joonseong Kang, Soojeong Lee, Subeen Park +5
In-Context Learning (ICL) enables Large Language Models (LLMs) to perform tasks without parameter updates by conditioning on a few demonstrations provided in the prompt. Despite it…