4 papers · 1 filter
DUD: Decoupled Update Dynamics for Reliable Uncertainty Quantification in Large Language Models
Yixin Bu, Runze Xia, Guanyun Zou +3
Accurate Uncertainty Quantification (UQ) is critical for reliable deployment of Large Language Models (LLMs), yet traditional probability-based metrics often fail to capture the mo…
Toward Culturally Aligned LLMs through Ontology-Guided Multi-Agent Reasoning
Wonduk Seo, Wonseok Choi, Junseo Koh +7
Large Language Models (LLMs) increasingly support culturally sensitive decision making, yet often exhibit misalignment due to skewed pretraining data and the absence of structured…
Better by Comparison: Retrieval-Augmented Contrastive Reasoning for Automatic Prompt Optimization
Juhyeon Lee, Wonduk Seo, Hyunjin An +2
Automatic prompt optimization has recently emerged as a strategy for improving the quality of prompts used in Large Language Models (LLMs), with the goal of generating more accurat…
ValuesRAG: Enhancing Cultural Alignment Through Retrieval-Augmented Contextual Learning
Wonduk Seo, Zonghao Yuan, Yi Bu
Ensuring cultural values alignment in Large Language Models (LLMs) remains a critical challenge, as these models often embed Western-centric biases from their training data, leadin…