Chinese Spell Checking (CSC) aims to detect and correct spelling errors in
sentences. Despite Large Language Models (LLMs) exhibit robust capabilities and
are widely applied in various tasks, their performance on CSC is often
unsatisfactory. We find that LLMs fail to meet the Chinese character-level
constraints of the CSC task, namely equal length and phonetic similarity,
leading to a performance bottleneck. Further analysis reveal that this issue
stems from the granularity of tokenization, as current mixed character-word
tokenization struggles to satisfy these character-level constraints. To address
this issue, we propose C-LLM, a Large Language Model-based Chinese Spell
Checking method that learns to check errors Character by Character.
Character-level tokenization enables the model to learn character-level
alignment, effectively mitigating issues related to character-level
constraints. Furthermore, CSC is simplified to replication-dominated and
substitution-supplemented tasks. Experiments on two CSC benchmarks demonstrate
that C-LLM achieves an average improvement of 10% over existing methods.
Specifically, it shows a 2.1% improvement in general scenarios and a
significant 12% improvement in vertical domain scenarios, establishing
state-of-the-art performance. The source code can be accessed at
this https URL

我们提出了一种基于大型语言模型的中文拼写检查方法 C-LLM，该方法通过逐个字符检查错误，实现了字符级别的对齐，从而有效地缓解了与字符级别约束相关的问题。在两个中文拼写检查基准测试中的实验表明，C-LLM 相比现有方法平均提升了 10％，在一般场景下提升了 2.1％，在垂直领域场景中有显著的 12％改进，达到了最先进的性能。

C-LLM: 逐字学习检测中文拼写错误

C-LLM: Learn to Check Chinese Spelling Errors Character by Character

The launch of ChatGPT in November 2022 precipitated a panic among some
educators while prompting qualified enthusiasm from others. Under the umbrella
term Generative AI, ChatGPT is an example of a range of technologies for the
delivery of computer-generated text, image, and other digitized media. This
paper examines the implications for education of one generative AI technology,
chatbots responding from large language models, or C-LLM. It reports on an
application of a C-LLM to AI review and assessment of complex student work. In
a concluding discussion, the paper explores the intrinsic limits of generative
AI, bound as it is to language corpora and their textual representation through
binary notation. Within these limits, we suggest the range of emerging and
potential applications of Generative AI in education.

本文探讨了一种生成模型技术 —— 来自大型语言模型的聊天机器人，并报告了一项将其应用于复杂学生作品的评估中的案例，然后讨论了生成 AI 的内在限制和潜在应用。