3 papers
cs.CL2026
IREA: Intermediate Representation-based Embedding Alignment for Normative RAG
Mirae Han, Sihyeong Yeom, Harksoo Kim
Large language models (LLMs) have shown strong performance across various tasks, but they still struggle with questions involving ethical judgment. Previous studies have attempted…
cs.CL2026
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…
cs.CL2026
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…