Advancing LLMs for Chinese Semantic Error Correction: Example Selection and Re-scoring

Hongyan Wu

doi:10.1016/j.eswa.2026.131925

Advancing LLMs for Chinese Semantic Error Correction: Example Selection and Re-scoring

2026-03-08

0

PRE

AI

DOI：10.1016/j.eswa.2026.131925

Original

Original request for help

Save

Abstract

En 中文

• We introduce a demonstration example selection strategy tailored for the complex CSEC. • Our selection strategy captures fine-grained information across multi-dimensions. • We design a re-scoring mechanism to determine optimal correction. • Results reveal that our methods applied to LLMs achieve promising improvements. • Our findings contribute to a deeper understanding of LLMs in CSEC.

Keywords:

Example Selection

Re-scoring Mechanism

Chinese Semantic Error Correction

Large Language Models

Fine-grained Information

Advancing LLMs for Chinese Semantic Error Correction: Example Selection and Re-scoring

Abstract

Journal

Organization