Self-Specialization: Uncovering Latent Expertise within Large Language Models
Keywords: Large Language Models, Self-Alignment, Instruction-Tuning, Specialization
Abstract: Recent works have demonstrated the effectiveness of self-alignment in which a large language model is, by itself, aligned to follow general instructions through the automatic generation of instructional data using a handful of human-written seeds. Instead of general alignment, in this work, we focus on self-alignment for expert domain specialization (e.g., biomedicine), discovering it to be very effective for improving zero-shot and few-shot performance in target domains of interest. As a preliminary, we first present the benchmark results of existing aligned models within a specialized domain, which reveals the marginal effect that "generic" instruction-following training has on downstream expert domains' performance. To remedy this, we explore self-specialization that leverages domain-specific unlabelled data and a few labeled seeds for the self-alignment process. When augmented with retrieval to reduce hallucination and enhance concurrency of the alignment, self-specialization offers an effective (and efficient) way of "carving out" an expert model out of a "generalist", pre-trained LLM where different domains of expertise are originally combined in a form of "superposition". Our experimental results on a biomedical domain show that our self-specialized model (30B) outperforms its base model, MPT-30B by a large margin and even surpasses larger popular models based on LLaMA-65B, highlighting its potential and practicality for specialization, especially considering its efficiency in terms of data and parameters. Our code will be released upon acceptance.
Primary Area: unsupervised, self-supervised, semi-supervised, and supervised representation learning
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 6554
Loading