Conifer: Improving Complex Constrained Instruction-Following Ability of Large Language Models
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_ | 1866911826509299712 |
|---|---|
| author | Sun, Haoran Liu, Lixin Li, Junjie Wang, Fengyu Dong, Baohua Lin, Ran Huang, Ruohui |
| author_facet | Sun, Haoran Liu, Lixin Li, Junjie Wang, Fengyu Dong, Baohua Lin, Ran Huang, Ruohui |
| contents | The ability of large language models (LLMs) to follow instructions is crucial to real-world applications. Despite recent advances, several studies have highlighted that LLMs struggle when faced with challenging instructions, especially those that include complex constraints, hindering their effectiveness in various tasks. To address this challenge, we introduce Conifer, a novel instruction tuning dataset, designed to enhance LLMs to follow multi-level instructions with complex constraints. Utilizing GPT-4, we curate the dataset by a series of LLM-driven refinement processes to ensure high quality. We also propose a progressive learning scheme that emphasizes an easy-to-hard progression, and learning from process feedback. Models trained with Conifer exhibit remarkable improvements in instruction-following abilities, especially for instructions with complex constraints. On several instruction-following benchmarks, our 7B model outperforms the state-of-the-art open-source 7B models, even exceeds the performance of models 10 times larger on certain metrics. All the code and Conifer dataset are available at https://www.github.com/ConiferLM/Conifer. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_02823 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Conifer: Improving Complex Constrained Instruction-Following Ability of Large Language Models Sun, Haoran Liu, Lixin Li, Junjie Wang, Fengyu Dong, Baohua Lin, Ran Huang, Ruohui Computation and Language Artificial Intelligence Machine Learning The ability of large language models (LLMs) to follow instructions is crucial to real-world applications. Despite recent advances, several studies have highlighted that LLMs struggle when faced with challenging instructions, especially those that include complex constraints, hindering their effectiveness in various tasks. To address this challenge, we introduce Conifer, a novel instruction tuning dataset, designed to enhance LLMs to follow multi-level instructions with complex constraints. Utilizing GPT-4, we curate the dataset by a series of LLM-driven refinement processes to ensure high quality. We also propose a progressive learning scheme that emphasizes an easy-to-hard progression, and learning from process feedback. Models trained with Conifer exhibit remarkable improvements in instruction-following abilities, especially for instructions with complex constraints. On several instruction-following benchmarks, our 7B model outperforms the state-of-the-art open-source 7B models, even exceeds the performance of models 10 times larger on certain metrics. All the code and Conifer dataset are available at https://www.github.com/ConiferLM/Conifer. |
| title | Conifer: Improving Complex Constrained Instruction-Following Ability of Large Language Models |
| topic | Computation and Language Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2404.02823 |