Making Small Language Models Better Multi-task Learners with Mixture-of-Task-Adapters

• URL: http://arxiv.org/abs/2309.11042v1
• Date: Wed, 20 Sep 2023 03:39:56 GMT
• Title: Making Small Language Models Better Multi-task Learners with Mixture-of-Task-Adapters
• Authors: Yukang Xie, Chengyu Wang, Junbing Yan, Jiyong Zhou, Feiqi Deng, Jun Huang
• Abstract summary: Large Language Models (LLMs) have achieved amazing zero-shot learning performance over a variety of Natural Language Processing (NLP) tasks. We present ALTER, a system that effectively builds the multi-tAsk learners with mixTure-of-task-adaptERs upon small language models. A two-stage training method is proposed to optimize the collaboration between adapters at a small computational cost.
• Score: 13.6682552098234
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recently, Large Language Models (LLMs) have achieved amazing zero-shot learning performance over a variety of Natural Language Processing (NLP) tasks, especially for text generative tasks. Yet, the large size of LLMs often leads to the high computational cost of model training and online deployment. In our work, we present ALTER, a system that effectively builds the multi-tAsk Learners with mixTure-of-task-adaptERs upon small language models (with <1B parameters) to address multiple NLP tasks simultaneously, capturing the commonalities and differences between tasks, in order to support domain-specific applications. Specifically, in ALTER, we propose the Mixture-of-Task-Adapters (MTA) module as an extension to the transformer architecture for the underlying model to capture the intra-task and inter-task knowledge. A two-stage training method is further proposed to optimize the collaboration between adapters at a small computational cost. Experimental results over a mixture of NLP tasks show that our proposed MTA architecture and the two-stage training method achieve good performance. Based on ALTER, we have also produced MTA-equipped language models for various domains.

Related papers

• Pilot: Building the Federated Multimodal Instruction Tuning Framework [79.56362403673354]
  Our framework integrates two stages of "adapter on adapter" into the connector of the vision encoder and the LLM. In stage 1, we extract task-specific features and client-specific features from visual information. In stage 2, we build the cross-task Mixture-of-Adapters(CT-MoA) module to perform cross-task interaction.
  arXiv  Detail & Related papers  (2025-01-23T07:49:24Z)
• Task Preference Optimization: Improving Multimodal Large Language Models with Vision Task Alignment [58.94611347128066]
  Task Preference Optimization (TPO) is a novel method that utilizes differentiable task preferences derived from typical fine-grained visual tasks. By leveraging rich visual labels during training, TPO significantly enhances the MLLM's multimodal capabilities and task-specific performance. Our instantiation of this approach with VideoChat and LLaVA demonstrates an overall 14.6% improvement in multimodal performance compared to baseline models.
  arXiv  Detail & Related papers  (2024-12-26T18:56:05Z)
• Optimizing Multi-Task Learning for Enhanced Performance in Large Language Models [5.930799903736776]
  The proposed multi-task learning model outperforms other comparison models in terms of text classification accuracy and ROUGE value of summary generation. The framework based on multi-task learning is expected to play a greater role in practical applications across fields.
  arXiv  Detail & Related papers  (2024-12-09T06:47:42Z)
• WavLLM: Towards Robust and Adaptive Speech Large Language Model [93.0773293897888]
  We introduce WavLLM, a robust and adaptive speech large language model with dual encoders, and a prompt-aware LoRA weight adapter. We validate the proposed model on universal speech benchmarks including tasks such as ASR, ST, SV, ER, and also apply it to specialized datasets like Gaokao English listening comprehension set for SQA, and speech Chain-of-Thought (CoT) evaluation set.
  arXiv  Detail & Related papers  (2024-03-31T12:01:32Z)
• Multitask Multimodal Prompted Training for Interactive Embodied Task Completion [48.69347134411864]
  Embodied MultiModal Agent (EMMA) is a unified encoder-decoder model that reasons over images and trajectories. By unifying all tasks as text generation, EMMA learns a language of actions which facilitates transfer across tasks.
  arXiv  Detail & Related papers  (2023-11-07T15:27:52Z)
• Task-Based MoE for Multitask Multilingual Machine Translation [58.20896429151824]
  Mixture-of-experts (MoE) architecture has been proven a powerful method for diverse tasks in training deep models in many applications. In this work, we design a novel method that incorporates task information into MoE models at different granular levels with shared dynamic task-based adapters.
  arXiv  Detail & Related papers  (2023-08-30T05:41:29Z)
• JiuZhang 2.0: A Unified Chinese Pre-trained Language Model for Multi-task Mathematical Problem Solving [77.51817534090789]
  We propose textbfJiuZhang2.0, a unified Chinese PLM specially for multi-task mathematical problem solving. Our idea is to maintain a moderate-sized model and employ the emphcross-task knowledge sharing to improve the model capacity in a multi-task setting.
  arXiv  Detail & Related papers  (2023-06-19T15:45:36Z)
• Multi-task Active Learning for Pre-trained Transformer-based Models [22.228551277598804]
  Multi-task learning, in which several tasks are jointly learned by a single model, allows NLP models to share information from multiple annotations. This technique requires annotating the same text with multiple annotation schemes which may be costly and laborious. Active learning (AL) has been demonstrated to optimize annotation processes by iteratively selecting unlabeled examples.
  arXiv  Detail & Related papers  (2022-08-10T14:54:13Z)

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.