5 papers
Is Discrete Difficulty Sufficient? Leveraging Continuous Difficulty for Efficient Self-Consistency in LLMs
Sihyeong Yeom, Geon Park, Geunyeong Jeong +3
Self-Consistency (SC) is a decoding strategy that samples diverse reasoning paths and selects the most consistent answer, demonstrating strong performance on complex reasoning prob…
Breaking the Pre-Sampling Barrier: Activation-Informed Difficulty-Aware Self-Consistency
Taewoong Yoon, Geunyeong Jeong, Geon Park +2
Self-Consistency (SC) is an effective decoding strategy that improves the reasoning performance of Large Language Models (LLMs) by generating multiple chain-of-thought reasoning pa…
K-EXAONE Technical Report
Eunbi Choi, Kibong Choi, Seokhee Hong +62
This technical report presents K-EXAONE, a large-scale multilingual language model developed by LG AI Research. K-EXAONE is built on a Mixture-of-Experts architecture with 236B tot…
STEAM: A Semantic-Level Knowledge Editing Framework for Large Language Models
Geunyeong Jeong, Juoh Sun, Seonghee Lee +1
Large Language Models store extensive factual knowledge acquired during large-scale pre-training. However, this knowledge is inherently static, reflecting only the state of the wor…
Exploring the Impact of Instruction-Tuning on LLM's Susceptibility to Misinformation
Kyubeen Han, Junseo Jang, Hongjin Kim +2
Instruction-tuning enhances the ability of large language models (LLMs) to follow user instructions more accurately, improving usability while reducing harmful outputs. However, th…