Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2410.10392 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913544932425728 |
|---|---|
| author | Li, Chenglin Chen, Qianglong Li, Zhi Tao, Feng Li, Yicheng Chen, Hao Yu, Fei Zhang, Yin |
| author_facet | Li, Chenglin Chen, Qianglong Li, Zhi Tao, Feng Li, Yicheng Chen, Hao Yu, Fei Zhang, Yin |
| contents | Instruction tuning is a crucial technique for aligning language models with humans' actual goals in the real world. Extensive research has highlighted the quality of instruction data is essential for the success of this alignment. However, creating high-quality data manually is labor-intensive and time-consuming, which leads researchers to explore using LLMs to synthesize data. Recent studies have focused on using a stronger LLM to iteratively enhance existing instruction data, showing promising results. Nevertheless, previous work often lacks control over the evolution direction, resulting in high uncertainty in the data synthesis process and low-quality instructions. In this paper, we introduce a general and scalable framework, IDEA-MCTS (Instruction Data Enhancement using Monte Carlo Tree Search), a scalable framework for efficiently synthesizing instructions. With tree search and evaluation models, it can efficiently guide each instruction to evolve into a high-quality form, aiding in instruction fine-tuning. Experimental results show that IDEA-MCTS significantly enhances the seed instruction data, raising the average evaluation scores of quality, diversity, and complexity from 2.19 to 3.81. Furthermore, in open-domain benchmarks, experimental results show that IDEA-MCTS improves the accuracy of real-world instruction-following skills in LLMs by an average of 5\% in low-resource settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_10392 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Optimizing Instruction Synthesis: Effective Exploration of Evolutionary Space with Tree Search Li, Chenglin Chen, Qianglong Li, Zhi Tao, Feng Li, Yicheng Chen, Hao Yu, Fei Zhang, Yin Artificial Intelligence Computation and Language Instruction tuning is a crucial technique for aligning language models with humans' actual goals in the real world. Extensive research has highlighted the quality of instruction data is essential for the success of this alignment. However, creating high-quality data manually is labor-intensive and time-consuming, which leads researchers to explore using LLMs to synthesize data. Recent studies have focused on using a stronger LLM to iteratively enhance existing instruction data, showing promising results. Nevertheless, previous work often lacks control over the evolution direction, resulting in high uncertainty in the data synthesis process and low-quality instructions. In this paper, we introduce a general and scalable framework, IDEA-MCTS (Instruction Data Enhancement using Monte Carlo Tree Search), a scalable framework for efficiently synthesizing instructions. With tree search and evaluation models, it can efficiently guide each instruction to evolve into a high-quality form, aiding in instruction fine-tuning. Experimental results show that IDEA-MCTS significantly enhances the seed instruction data, raising the average evaluation scores of quality, diversity, and complexity from 2.19 to 3.81. Furthermore, in open-domain benchmarks, experimental results show that IDEA-MCTS improves the accuracy of real-world instruction-following skills in LLMs by an average of 5\% in low-resource settings. |
| title | Optimizing Instruction Synthesis: Effective Exploration of Evolutionary Space with Tree Search |
| topic | Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2410.10392 |