Improving Cross-Domain Low-Resource Text Generation through LLM Post-Editing: A Programmer-Interpreter Approach
This addresses the challenge of maintaining domain generalization in LLM post-editing for text-generation tasks, offering an incremental improvement over existing methods.
The paper tackled the problem of improving cross-domain text generation by LLMs through post-editing, proposing a programmer-interpreter approach that enhances GPT-3.5's performance in logical form-to-text conversion and low-resource machine translation, surpassing other SOTA methods.
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.