Self-Specialization: Uncovering Latent Expertise within Large Language Models

• URL: http://arxiv.org/abs/2310.00160v2
• Date: Wed, 5 Jun 2024 19:48:45 GMT
• Title: Self-Specialization: Uncovering Latent Expertise within Large Language Models
• Authors: Junmo Kang, Hongyin Luo, Yada Zhu, Jacob Hansen, James Glass, David Cox, Alan Ritter, Rogerio Feris, Leonid Karlinsky,
• Abstract summary: Recent works have demonstrated the effectiveness of self-alignment in which a large language model is aligned to follow general instructions. We focus on self-alignment for expert domain specialization. We show that our self-specialized models outperform their base models by a large margin.
• Score: 39.04128008742973
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Recent works have demonstrated the effectiveness of self-alignment in which a large language model is aligned to follow general instructions using instructional data generated from the model itself starting from 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, finance). As a preliminary, we quantitively show the marginal effect that generic instruction-following training has on downstream expert domains' performance. To remedy this, we propose self-specialization - allowing for effective model specialization while achieving cross-task generalization by leveraging only a few labeled seeds. Self-specialization offers a data- and parameter-efficient way of "carving out" an expert model out of a generalist pre-trained LLM. Exploring a variety of popular open large models as a base for specialization, our experimental results in both biomedical and financial domains show that our self-specialized models outperform their base models by a large margin, and even larger models that are generally instruction-tuned or that have been adapted to the target domain by other means.

Related papers

• LFME: A Simple Framework for Learning from Multiple Experts in Domain Generalization [61.16890890570814]
  Domain generalization (DG) methods aim to maintain good performance in an unseen target domain by using training data from multiple source domains. This work introduces a simple yet effective framework, dubbed learning from multiple experts (LFME) that aims to make the target model an expert in all source domains to improve DG.
  arXiv  Detail & Related papers  (2024-10-22T13:44:10Z)
• Task-Adaptive Pretrained Language Models via Clustered-Importance Sampling [21.762562172089236]
  We build specialist models from large generalist training sets instead. We adjust the training distribution of the generalist data with guidance from the limited domain-specific data. It is scalable, suitable for pretraining and continued pretraining, it works well in multi-task settings.
  arXiv  Detail & Related papers  (2024-09-30T20:49:54Z)
• LoRKD: Low-Rank Knowledge Decomposition for Medical Foundation Models [59.961172635689664]
  "Knowledge Decomposition" aims to improve the performance on specific medical tasks. We propose a novel framework named Low-Rank Knowledge Decomposition (LoRKD) LoRKD explicitly separates gradients from different tasks by incorporating low-rank expert modules and efficient knowledge separation convolution.
  arXiv  Detail & Related papers  (2024-09-29T03:56:21Z)
• Revisiting SMoE Language Models by Evaluating Inefficiencies with Task Specific Expert Pruning [78.72226641279863]
  Sparse Mixture of Expert (SMoE) models have emerged as a scalable alternative to dense models in language modeling. Our research explores task-specific model pruning to inform decisions about designing SMoE architectures. We introduce an adaptive task-aware pruning technique UNCURL to reduce the number of experts per MoE layer in an offline manner post-training.
  arXiv  Detail & Related papers  (2024-09-02T22:35:03Z)
• Prompting Encoder Models for Zero-Shot Classification: A Cross-Domain Study in Italian [75.94354349994576]
  This paper explores the feasibility of employing smaller, domain-specific encoder LMs alongside prompting techniques to enhance performance in specialized contexts. Our study concentrates on the Italian bureaucratic and legal language, experimenting with both general-purpose and further pre-trained encoder-only models. The results indicate that while further pre-trained models may show diminished robustness in general knowledge, they exhibit superior adaptability for domain-specific tasks, even in a zero-shot setting.
  arXiv  Detail & Related papers  (2024-07-30T08:50:16Z)
• VANER: Leveraging Large Language Model for Versatile and Adaptive Biomedical Named Entity Recognition [3.4923338594757674]
  Large language models (LLMs) can be used to train a model capable of extracting various types of entities. In this paper, we utilize the open-sourced LLM LLaMA2 as the backbone model, and design specific instructions to distinguish between different types of entities and datasets. Our model VANER, trained with a small partition of parameters, significantly outperforms previous LLMs-based models and, for the first time, as a model based on LLM, surpasses the majority of conventional state-of-the-art BioNER systems.
  arXiv  Detail & Related papers  (2024-04-27T09:00:39Z)
• On Good Practices for Task-Specific Distillation of Large Pretrained Visual Models [42.57860180847724]
  We show that the excellent robustness and versatility of recent pretrained models challenge common practices established in the literature. We also show that a variant of Mixup based on stable diffusion complements standard data augmentation.
  arXiv  Detail & Related papers  (2024-02-17T15:15:43Z)
• Learning to Route Among Specialized Experts for Zero-Shot Generalization [39.56470042680907]
  We propose Post-Hoc Adaptive Tokenwise Gating Over an Ocean of Specialized Experts (PHATGOOSE) It learns to route among specialized modules that were produced through parameter-efficient fine-tuning. It does not require simultaneous access to the datasets used to create the specialized models and only requires a modest amount of additional compute after each expert model is trained.
  arXiv  Detail & Related papers  (2024-02-08T17:43:22Z)
• Fantastic Gains and Where to Find Them: On the Existence and Prospect of General Knowledge Transfer between Any Pretrained Model [74.62272538148245]
  We show that for arbitrary pairings of pretrained models, one model extracts significant data context unavailable in the other. We investigate if it is possible to transfer such "complementary" knowledge from one model to another without performance degradation.
  arXiv  Detail & Related papers  (2023-10-26T17:59:46Z)
• Domain Generalization using Pretrained Models without Fine-tuning [25.489714555859944]
  Fine-tuning pretrained models is a common practice in domain generalization (DG) tasks. We propose a novel domain generalization paradigm to better leverage various pretrained models, named specialized ensemble learning for domain generalization (SEDGE) SEDGE achieves significant performance improvements comparing to strong baselines including state-of-the-art method in DG tasks.
  arXiv  Detail & Related papers  (2022-03-09T09:33:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.