4 papers
Shared Semantics, Divergent Mechanisms: Unsupervised Feature Discovery by Aligning Semantics and Mechanisms
Hyunjin Cho, Youngji Roh, Jaehyung Kim
As large language models are increasingly deployed in high-stakes settings, there is a growing need for tools that audit not only model outputs but also the internal computations t…
Embracing Anisotropy: Turning Massive Activations into Interpretable Control Knobs for Large Language Models
Youngji Roh, Hyunjin Cho, Jaehyung Kim
Large Language Models (LLMs) exhibit highly anisotropic internal representations, often characterized by massive activations, a phenomenon where a small subset of feature dimension…
Review-driven Personalized Preference Reasoning with Large Language Models for Recommendation
Jieyong Kim, Hyunseo Kim, Hyunjin Cho +4
Recent advancements in Large Language Models (LLMs) have demonstrated exceptional performance across a wide range of tasks, generating significant interest in their application to…
Evidence-Focused Fact Summarization for Knowledge-Augmented Zero-Shot Question Answering
Sungho Ko, Hyunjin Cho, Hyungjoo Chae +2
Recent studies have investigated utilizing Knowledge Graphs (KGs) to enhance Quesetion Answering (QA) performance of Large Language Models (LLMs), yet structured KG verbalization r…