4 papers
MechELK: A Mechanistic Interpretability Framework for Eliciting Latent Knowledge in Large Language Models
Ji-jun Park, Soo-joon Choi, Jiwon Jeong +2
Large language models (LLMs) frequently encode factual and reasoning knowledge in their internal representations that is not faithfully reflected in their surface-level outputs --…
ContextualLVLM-Agent: A Holistic Framework for Multi-Turn Visually-Grounded Dialogue and Complex Instruction Following
Seungmin Han, Haeun Kwon, Ji-jun Park +1
Despite significant advancements in Large Language Models (LLMs) and Large Vision-Language Models (LVLMs), current models still face substantial challenges in handling complex, mul…
Harnessing Generative LLMs for Enhanced Financial Event Entity Extraction Performance
Soo-joon Choi, Ji-jun Park
Financial event entity extraction is a crucial task for analyzing market dynamics and building financial knowledge graphs, yet it presents significant challenges due to the special…
Bridging Vision and Language: Modeling Causality and Temporality in Video Narratives
Ji-jun Park, Soo-joon Choi
Video captioning is a critical task in the field of multimodal machine learning, aiming to generate descriptive and coherent textual narratives for video content. While large visio…