Pruning as a Domain-specific LLM Extractor
Publication Date: 6/20/2024
Event: 2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2024), Mexico City, Mexico
Reference: pp. 1417-1428, 2024
Authors: Nan Zhang, The Pennsylvania State University; NEC Laboratories America, Inc.; Yanchi Liu, NEC Laboratories America, Inc.; Xujiang Zhao, NEC Laboratories America, Inc.; Wei Cheng, NEC Laboratories America, Inc.; Runxue Bao, GE HealthCare; Rui Zhang, The Pennsylvania State University; Prasenjit Mitra, The Pennsylvania State University; Haifeng Chen, NEC Laboratories America, Inc.
Abstract: Large Language Models (LLMs) have exhibited remarkable proficiency across a wide array of NLP tasks. However, the escalation in model size also engenders substantial deployment costs. While few efforts have explored model pruning techniques to reduce the size of LLMs, they mainly center on general or task-specific weights. This leads to suboptimal performance due to lacking specificity on the target domain or generality on different tasks when applied to domain-specific challenges. This work introduces an innovative unstructured dual-pruning methodology, D-PRUNER, for domain-specific compression on LLM. It extracts a compressed, domain-specific, and task agnostic LLM by identifying LLM weights that are pivotal for general capabilities, like linguistic capability and multi-task solving, and domain-specific knowledge. More specifically, we first assess general weight importance by quantifying the error incurred upon their removal with the help of an open-domain calibration dataset. Then, we utilize this general weight importance to refine the training loss, so that it preserves generality when fitting into a specific domain. Moreover, by efficiently approximating weight importance with the refined training loss on a domain-specific calibration dataset, we obtain a pruned model emphasizing generality and specificity. Our comprehensive experiments across various tasks in healthcare and legal domains show the effectiveness of D-PRUNER in domain-specific compression. Our code is available at https: //github.com/psunlpgroup/D-Pruner.
Publication Link: https://aclanthology.org/2024.findings-naacl.91.pdf