通过LLM后编辑改进跨域低资源文本生成：一种程序员-解释器方法
Improving Cross-Domain Low-Resource Text Generation through LLM Post-Editing: A Programmer-Interpreter Approach
AI总结：
提出神经程序员-解释器后编辑框架，保留LLM跨域泛化能力，设计专门编辑动作，显著提升GPT-3.5在逻辑形式转换和低资源机器翻译中的性能。
摘要：
后编辑已被证明能有效提升大型语言模型（LLM）如GPT-3.5或GPT-4生成文本的质量，尤其是在直接更新其参数以提升文本质量不可行或成本高昂的情况下。然而，仅依赖较小的语言模型进行后编辑会限制LLM跨域泛化的能力。此外，这些方法中的编辑策略并非针对文本生成任务最优设计。为解决这些局限，我们提出一种神经程序员-解释器方法，在编辑LLM输出时保留其跨域泛化能力。该框架中的编辑动作专门为文本生成设计。大量实验表明，程序员-解释器显著提升了GPT-3.5在逻辑形式到文本转换和低资源机器翻译中的性能，在跨域设置中超越了其他最先进的（SOTA）LLM后编辑方法。
英文摘要：
Post-editing has proven effective in improving the quality of text generated by large language models (LLMs) such as GPT-3.5 or GPT-4, particularly when direct updating of their parameters to enhance text quality is infeasible or expensive. However, relying solely on smaller language models for post-editing can limit the LLMs' ability to generalize across domains. Moreover, the editing strategies in these methods are not optimally designed for text-generation tasks. To address these limitations, we propose a neural programmer-interpreter approach that preserves the domain generalization ability of LLMs when editing their output. The editing actions in this framework are specifically devised for text generation. Extensive experiments demonstrate that the programmer-interpreter significantly enhances GPT-3.5's performance in logical form-to-text conversion and low-resource machine translation, surpassing other state-of-the-art (SOTA) LLM post-editing methods in cross-domain settings.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
