SED: Self-Evaluation Decoding Enhances Large Language Models for Better Generation

[PDF] arxiv.org

Internal consistency and self-feedback in large language models: A survey

X Liang, S Song, Z Zheng, H Wang, Q Yu, X Li… - arXiv preprint arXiv …, 2024 - arxiv.org
Large language models (LLMs) often exhibit deficient reasoning or generate hallucinations.
To address these, studies prefixed with" Self-" such as Self-Consistency, Self-Improve, and …
被引用次数：20 相关文章 所有 4 个版本
[PDF] arxiv.org

HARP: Hesitation-Aware Reframing in Transformer Inference Pass

R Storaï, S Hwang - arXiv preprint arXiv:2412.07282, 2024 - arxiv.org
This paper aims to improve the performance of large language models by addressing the
variable computational demands in inference steps, where some tokens require more …
相关文章 所有 2 个版本