Improving Cross-Domain Low-Resource Text Generation through LLM Post-Editing: A Programmer-Interpreter Approach
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911772717350912 |
|---|---|
| author | Li, Zhuang Haroutunian, Levon Tumuluri, Raj Cohen, Philip Haffari, Gholamreza |
| author_facet | Li, Zhuang Haroutunian, Levon Tumuluri, Raj Cohen, Philip Haffari, Gholamreza |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_04609 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Improving Cross-Domain Low-Resource Text Generation through LLM Post-Editing: A Programmer-Interpreter Approach Li, Zhuang Haroutunian, Levon Tumuluri, Raj Cohen, Philip Haffari, Gholamreza Computation and Language 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. |
| title | Improving Cross-Domain Low-Resource Text Generation through LLM Post-Editing: A Programmer-Interpreter Approach |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2402.04609 |