AutoAdapt: An Automated Domain Adaptation Framework for LLMs
This work provides an automated solution for efficient and reliable domain adaptation of LLMs, benefiting researchers and practitioners working with specialized data.
Large language models (LLMs) struggle in specialized domains due to manual, costly, and complex adaptation processes. AutoAdapt, an automated framework, addresses this by using curated knowledge bases and a multi-agent debating system to streamline adaptation, achieving a 25% average relative accuracy improvement over state-of-the-art baselines across 10 tasks.
Large language models (LLMs) excel in open domains but struggle in specialized settings with limited data and evolving knowledge. Existing domain adaptation practices rely heavily on manual trial-and-error processes, incur significant hyperparameter complexity, and are highly sensitive to data and user preferences, all under the high cost of LLM training. Moreover, the interactions and transferability of hyperparameter choices across models/domains remain poorly understood, making adaptation gains uncertain even with substantial effort. To solve these challenges, we present AutoAdapt, a novel end-to-end automated framework for efficient and reliable LLM domain adaptation. AutoAdapt leverages curated knowledge bases from literature and open-source resources to reduce expert intervention. To narrow the search space, we design a novel multi-agent debating system in which proposal and critic agents iteratively interact to align user intent and incorporate data signals and best practices into the planning process. To optimize hyperparameters under tight budgets, we propose AutoRefine, a novel LLM-based surrogate that replaces costly black-box search. Across 10 tasks, AutoAdapt achieves a 25% average relative accuracy improvement over state-of-the-art Automated Machine Learning baselines with minimal overhead.