Active Domain Knowledge Acquisition with 100-Dollar Budget: Enhancing LLMs via Cost-Efficient, Expert-Involved Interaction in Sensitive Domains

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Wu, Yang, Moraffah, Raha, Yao, Rujing, Yu, Jinhong, Tao, Zhimin, Liu, Xiaozhong
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908509292986368
author Wu, Yang
Moraffah, Raha
Yao, Rujing
Yu, Jinhong
Tao, Zhimin
Liu, Xiaozhong
author_facet Wu, Yang
Moraffah, Raha
Yao, Rujing
Yu, Jinhong
Tao, Zhimin
Liu, Xiaozhong
contents Large Language Models (LLMs) have demonstrated an impressive level of general knowledge. However, they often struggle in highly specialized and cost-sensitive domains such as drug discovery and rare disease research due to the lack of expert knowledge. In this paper, we propose a novel framework (PU-ADKA) designed to efficiently enhance domain-specific LLMs by actively engaging domain experts within a fixed budget. Unlike traditional fine-tuning approaches, PU-ADKA selectively identifies and queries the most appropriate expert from a team, taking into account each expert's availability, knowledge boundaries, and consultation costs. We train PU-ADKA using simulations on PubMed data and validate it through both controlled expert interactions and real-world deployment with a drug development team, demonstrating its effectiveness in enhancing LLM performance in specialized domains under strict budget constraints. In addition to outlining our methodological innovations and experimental results, we introduce a new benchmark dataset, CKAD, for cost-effective LLM domain knowledge acquisition to foster further research in this challenging area.
format Preprint
id arxiv_https___arxiv_org_abs_2508_17202
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Active Domain Knowledge Acquisition with 100-Dollar Budget: Enhancing LLMs via Cost-Efficient, Expert-Involved Interaction in Sensitive Domains
Wu, Yang
Moraffah, Raha
Yao, Rujing
Yu, Jinhong
Tao, Zhimin
Liu, Xiaozhong
Computation and Language
Large Language Models (LLMs) have demonstrated an impressive level of general knowledge. However, they often struggle in highly specialized and cost-sensitive domains such as drug discovery and rare disease research due to the lack of expert knowledge. In this paper, we propose a novel framework (PU-ADKA) designed to efficiently enhance domain-specific LLMs by actively engaging domain experts within a fixed budget. Unlike traditional fine-tuning approaches, PU-ADKA selectively identifies and queries the most appropriate expert from a team, taking into account each expert's availability, knowledge boundaries, and consultation costs. We train PU-ADKA using simulations on PubMed data and validate it through both controlled expert interactions and real-world deployment with a drug development team, demonstrating its effectiveness in enhancing LLM performance in specialized domains under strict budget constraints. In addition to outlining our methodological innovations and experimental results, we introduce a new benchmark dataset, CKAD, for cost-effective LLM domain knowledge acquisition to foster further research in this challenging area.
title Active Domain Knowledge Acquisition with 100-Dollar Budget: Enhancing LLMs via Cost-Efficient, Expert-Involved Interaction in Sensitive Domains
topic Computation and Language
url https://arxiv.org/abs/2508.17202