Jungsuk Oh

Latent Self-Consistency for Reliable Majority-Set Selection in Short- and Long-Answer Reasoning

Probabilistic decoding in Large Language Models (LLMs) often yields inconsistent outputs, particularly on complex or long-form questions. Self-Consistency (SC) mitigates this for short-form QA by majority voting over exact strings, whereas Universal Self-Consistency (USC) and Weighted Unigram Consis