SciInstruct: a Self-Reflective Instruction Annotated Dataset for Training Scientific Language Models
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912121424445440 |
|---|---|
| author | Zhang, Dan Hu, Ziniu Zhoubian, Sining Du, Zhengxiao Yang, Kaiyu Wang, Zihan Yue, Yisong Dong, Yuxiao Tang, Jie |
| author_facet | Zhang, Dan Hu, Ziniu Zhoubian, Sining Du, Zhengxiao Yang, Kaiyu Wang, Zihan Yue, Yisong Dong, Yuxiao Tang, Jie |
| contents | Large Language Models (LLMs) have shown promise in assisting scientific discovery. However, such applications are currently limited by LLMs' deficiencies in understanding intricate scientific concepts, deriving symbolic equations, and solving advanced numerical calculations. To bridge these gaps, we introduce SciInstruct, a suite of scientific instructions for training scientific language models capable of college-level scientific reasoning. Central to our approach is a novel self-reflective instruction annotation framework to address the data scarcity challenge in the science domain. This framework leverages existing LLMs to generate step-by-step reasoning for unlabelled scientific questions, followed by a process of self-reflective critic-and-revise. Applying this framework, we curated a diverse and high-quality dataset encompassing physics, chemistry, math, and formal proofs. We analyze the curated SciInstruct from multiple interesting perspectives (e.g., domain, scale, source, question type, answer length, etc.). To verify the effectiveness of SciInstruct, we fine-tuned different language models with SciInstruct, i.e., ChatGLM3 (6B and 32B), Llama3-8B-Instruct, and Mistral-7B: MetaMath, enhancing their scientific and mathematical reasoning capabilities, without sacrificing the language understanding capabilities of the base model. We release all codes and SciInstruct at https://github.com/THUDM/SciGLM. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_07950 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SciInstruct: a Self-Reflective Instruction Annotated Dataset for Training Scientific Language Models Zhang, Dan Hu, Ziniu Zhoubian, Sining Du, Zhengxiao Yang, Kaiyu Wang, Zihan Yue, Yisong Dong, Yuxiao Tang, Jie Computation and Language Large Language Models (LLMs) have shown promise in assisting scientific discovery. However, such applications are currently limited by LLMs' deficiencies in understanding intricate scientific concepts, deriving symbolic equations, and solving advanced numerical calculations. To bridge these gaps, we introduce SciInstruct, a suite of scientific instructions for training scientific language models capable of college-level scientific reasoning. Central to our approach is a novel self-reflective instruction annotation framework to address the data scarcity challenge in the science domain. This framework leverages existing LLMs to generate step-by-step reasoning for unlabelled scientific questions, followed by a process of self-reflective critic-and-revise. Applying this framework, we curated a diverse and high-quality dataset encompassing physics, chemistry, math, and formal proofs. We analyze the curated SciInstruct from multiple interesting perspectives (e.g., domain, scale, source, question type, answer length, etc.). To verify the effectiveness of SciInstruct, we fine-tuned different language models with SciInstruct, i.e., ChatGLM3 (6B and 32B), Llama3-8B-Instruct, and Mistral-7B: MetaMath, enhancing their scientific and mathematical reasoning capabilities, without sacrificing the language understanding capabilities of the base model. We release all codes and SciInstruct at https://github.com/THUDM/SciGLM. |
| title | SciInstruct: a Self-Reflective Instruction Annotated Dataset for Training Scientific Language Models |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2401.07950 |