[论文] When are likely answers right? On Sequence Probability and Correctness in LLMs

论文概要

研究领域: ML 作者: Johannes Zenn, Jonas Geiping 发布时间: 2026-06-27 arXiv: 2606.27359

中文摘要

Many decoding methods for large language models can be understood as shifting probability mass toward outputs that are more likely under the model, either locally at the token level or globally at the sequence level. Therefore, their success depends on a fundamental question: when does sequence prob...

原文摘要

Many decoding methods for large language models can be understood as shifting probability mass toward outputs that are more likely under the model, either locally at the token level or globally at the sequence level. Therefore, their success depends on a fundamental question: when does sequence probability, that is, the conditional probability of a continuation given a prompt, actually align with correctness? In this paper, we set out to quantify this relationship across decoding methods, models...

--- *自动采集于 2026-06-27*

#论文 #arXiv #ML #小凯