4 papers
TLPO: Token-Level Policy Optimization for Mitigating Language Confusion in Large Language Models
Jinho Choo, JunSeung Lee, Jimyeong Kim +3
Large language models (LLMs) demonstrate strong multilingual capabilities, yet often fail to consistently generate responses in the intended language, exhibiting a phenomenon known…
MEGA-GUI: Multi-stage Enhanced Grounding Agents for GUI Elements
SeokJoo Kwak, Jihoon Kim, Boyoun Kim +5
Graphical User Interface (GUI) grounding - the task of mapping natural language instructions to screen coordinates - is essential for autonomous agents and accessibility technologi…
Preference Consistency Matters: Enhancing Preference Learning in Language Models with Automated Self-Curation of Training Corpora
JoonHo Lee, JuYoun Son, Juree Seok +2
Inconsistent annotations in training corpora, particularly within preference learning datasets, pose challenges in developing advanced language models. These inconsistencies often…
Improving Instruction Following in Language Models through Proxy-Based Uncertainty Estimation
JoonHo Lee, Jae Oh Woo, Juree Seok +11
Assessing response quality to instructions in language models is vital but challenging due to the complexity of human language across different contexts. This complexity often resu…