Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2403.15736 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916478752653312 |
|---|---|
| author | Zhang, Xin Ju, Tianjie Liang, Huijia Fu, Ying Zhang, Qin |
| author_facet | Zhang, Xin Ju, Tianjie Liang, Huijia Fu, Ying Zhang, Qin |
| contents | The substantial interest in updating Large Language Models (LLMs) without retraining from scratch is accompanied by several challenges. This is particularly true when updating LLMs with datasets that necessitate domain-expert reasoning across extensive texts, despite limited samples. We termed the scenario as the Few-Shot Domain-Expert Reasoning for Updating LLMs (FDoR-UL). Traditional methods such as Low-Rank Adaptation (LoRA) and Retrieval Augmented Generation (RAG) are inadequate for addressing this critical issue, particularly evident in our exploration of a specific medical dataset that epitomizes the distinct needs of FDoR-UL. To tackle this challenge, we introduce a Sequential Fusion method to integrate knowledge from complex contexts into LLMs. This method employs a two-stage framework: initially leveraging general LLMs to perform relation extraction for knowledge acquisition from complex texts, followed by updating domain-specific LLMs through Knowledge Editing (KE). Employing our method, domain-specific LLMs achieved a 71.7% accuracy (an average gain of 39.1%) in question-answering tasks. Furthermore, we expanded our evaluation to a novel economics-management dataset we developed, where our method achieved a 75.0% accuracy (an average gain of 45.0%). These findings underscore the effectiveness and flexibility of our approach in FDoR-UL across various domains. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_15736 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | General LLMs as Instructors for Domain-Specific LLMs: A Sequential Fusion Method to Integrate Extraction and Editing Zhang, Xin Ju, Tianjie Liang, Huijia Fu, Ying Zhang, Qin Computation and Language The substantial interest in updating Large Language Models (LLMs) without retraining from scratch is accompanied by several challenges. This is particularly true when updating LLMs with datasets that necessitate domain-expert reasoning across extensive texts, despite limited samples. We termed the scenario as the Few-Shot Domain-Expert Reasoning for Updating LLMs (FDoR-UL). Traditional methods such as Low-Rank Adaptation (LoRA) and Retrieval Augmented Generation (RAG) are inadequate for addressing this critical issue, particularly evident in our exploration of a specific medical dataset that epitomizes the distinct needs of FDoR-UL. To tackle this challenge, we introduce a Sequential Fusion method to integrate knowledge from complex contexts into LLMs. This method employs a two-stage framework: initially leveraging general LLMs to perform relation extraction for knowledge acquisition from complex texts, followed by updating domain-specific LLMs through Knowledge Editing (KE). Employing our method, domain-specific LLMs achieved a 71.7% accuracy (an average gain of 39.1%) in question-answering tasks. Furthermore, we expanded our evaluation to a novel economics-management dataset we developed, where our method achieved a 75.0% accuracy (an average gain of 45.0%). These findings underscore the effectiveness and flexibility of our approach in FDoR-UL across various domains. |
| title | General LLMs as Instructors for Domain-Specific LLMs: A Sequential Fusion Method to Integrate Extraction and Editing |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2403.15736 |