DRAK: Unlocking Molecular Insights with Domain-Specific Retrieval-Augmented Knowledge in LLMs
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916303233613824 |
|---|---|
| author | Liu, Jinzhe Huang, Xiangsheng Chen, Zhuo Fang, Yin |
| author_facet | Liu, Jinzhe Huang, Xiangsheng Chen, Zhuo Fang, Yin |
| contents | Large Language Models (LLMs) encounter challenges with the unique syntax of specific domains, such as biomolecules. Existing fine-tuning or modality alignment techniques struggle to bridge the domain knowledge gap and understand complex molecular data, limiting LLMs' progress in specialized fields. To overcome these limitations, we propose an expandable and adaptable non-parametric knowledge injection framework named Domain-specific Retrieval-Augmented Knowledge (DRAK), aimed at enhancing reasoning capabilities in specific domains. Utilizing knowledge-aware prompts and gold label-induced reasoning, DRAK has developed profound expertise in the molecular domain and the capability to handle a broad spectrum of analysis tasks. We evaluated two distinct forms of DRAK variants, proving that DRAK exceeds previous benchmarks on six molecular tasks within the Mol-Instructions dataset. Extensive experiments have underscored DRAK's formidable performance and its potential to unlock molecular insights, offering a unified paradigm for LLMs to tackle knowledge-intensive tasks in specific domains. Our code will be available soon. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_18535 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | DRAK: Unlocking Molecular Insights with Domain-Specific Retrieval-Augmented Knowledge in LLMs Liu, Jinzhe Huang, Xiangsheng Chen, Zhuo Fang, Yin Biomolecules Artificial Intelligence Information Retrieval Large Language Models (LLMs) encounter challenges with the unique syntax of specific domains, such as biomolecules. Existing fine-tuning or modality alignment techniques struggle to bridge the domain knowledge gap and understand complex molecular data, limiting LLMs' progress in specialized fields. To overcome these limitations, we propose an expandable and adaptable non-parametric knowledge injection framework named Domain-specific Retrieval-Augmented Knowledge (DRAK), aimed at enhancing reasoning capabilities in specific domains. Utilizing knowledge-aware prompts and gold label-induced reasoning, DRAK has developed profound expertise in the molecular domain and the capability to handle a broad spectrum of analysis tasks. We evaluated two distinct forms of DRAK variants, proving that DRAK exceeds previous benchmarks on six molecular tasks within the Mol-Instructions dataset. Extensive experiments have underscored DRAK's formidable performance and its potential to unlock molecular insights, offering a unified paradigm for LLMs to tackle knowledge-intensive tasks in specific domains. Our code will be available soon. |
| title | DRAK: Unlocking Molecular Insights with Domain-Specific Retrieval-Augmented Knowledge in LLMs |
| topic | Biomolecules Artificial Intelligence Information Retrieval |
| url | https://arxiv.org/abs/2406.18535 |