AIR: Complex Instruction Generation via Automatic Iterative Refinement
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917938715426816 |
|---|---|
| author | Liu, Wei He, Yancheng Huang, Hui Hu, Chengwei Liu, Jiaheng Li, Shilong Su, Wenbo Zheng, Bo |
| author_facet | Liu, Wei He, Yancheng Huang, Hui Hu, Chengwei Liu, Jiaheng Li, Shilong Su, Wenbo Zheng, Bo |
| contents | With the development of large language models, their ability to follow simple instructions has significantly improved. However, adhering to complex instructions remains a major challenge. Current approaches to generating complex instructions are often irrelevant to the current instruction requirements or suffer from limited scalability and diversity. Moreover, methods such as back-translation, while effective for simple instruction generation, fail to leverage the rich contents and structures in large web corpora. In this paper, we propose a novel automatic iterative refinement framework to generate complex instructions with constraints, which not only better reflects the requirements of real scenarios but also significantly enhances LLMs' ability to follow complex instructions. The AIR framework consists of two stages: (1)Generate an initial instruction from a document; (2)Iteratively refine instructions with LLM-as-judge guidance by comparing the model's output with the document to incorporate valuable constraints. Finally, we construct the AIR-10K dataset with 10K complex instructions and demonstrate that instructions generated with our approach significantly improve the model's ability to follow complex instructions, outperforming existing methods for instruction generation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_17787 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AIR: Complex Instruction Generation via Automatic Iterative Refinement Liu, Wei He, Yancheng Huang, Hui Hu, Chengwei Liu, Jiaheng Li, Shilong Su, Wenbo Zheng, Bo Computation and Language Artificial Intelligence With the development of large language models, their ability to follow simple instructions has significantly improved. However, adhering to complex instructions remains a major challenge. Current approaches to generating complex instructions are often irrelevant to the current instruction requirements or suffer from limited scalability and diversity. Moreover, methods such as back-translation, while effective for simple instruction generation, fail to leverage the rich contents and structures in large web corpora. In this paper, we propose a novel automatic iterative refinement framework to generate complex instructions with constraints, which not only better reflects the requirements of real scenarios but also significantly enhances LLMs' ability to follow complex instructions. The AIR framework consists of two stages: (1)Generate an initial instruction from a document; (2)Iteratively refine instructions with LLM-as-judge guidance by comparing the model's output with the document to incorporate valuable constraints. Finally, we construct the AIR-10K dataset with 10K complex instructions and demonstrate that instructions generated with our approach significantly improve the model's ability to follow complex instructions, outperforming existing methods for instruction generation. |
| title | AIR: Complex Instruction Generation via Automatic Iterative Refinement |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2502.17787 |