Cheap Learning: Maximising Performance of Language Models for Social Data Science Using Minimal Data

• URL: http://arxiv.org/abs/2401.12295v1
• Date: Mon, 22 Jan 2024 19:00:11 GMT
• Title: Cheap Learning: Maximising Performance of Language Models for Social Data Science Using Minimal Data
• Authors: Leonardo Castro-Gonzalez and Yi-Ling Chung and Hannak Rose Kirk and John Francis and Angus R. Williams and Pica Johansson and Jonathan Bright
• Abstract summary: We review three cheap' techniques that have developed in recent years: weak supervision, transfer learning and prompt engineering. For the latter, we review the particular case of zero-shot prompting of large language models. We show good performance for all techniques, and in particular we demonstrate how prompting of large language models can achieve high accuracy at very low cost.
• Score: 1.8692054990918079
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The field of machine learning has recently made significant progress in reducing the requirements for labelled training data when building new models. These `cheaper' learning techniques hold significant potential for the social sciences, where development of large labelled training datasets is often a significant practical impediment to the use of machine learning for analytical tasks. In this article we review three `cheap' techniques that have developed in recent years: weak supervision, transfer learning and prompt engineering. For the latter, we also review the particular case of zero-shot prompting of large language models. For each technique we provide a guide of how it works and demonstrate its application across six different realistic social science applications (two different tasks paired with three different dataset makeups). We show good performance for all techniques, and in particular we demonstrate how prompting of large language models can achieve high accuracy at very low cost. Our results are accompanied by a code repository to make it easy for others to duplicate our work and use it in their own research. Overall, our article is intended to stimulate further uptake of these techniques in the social sciences.

Related papers

• AI Competitions and Benchmarks: Dataset Development [42.164845505628506]
  This chapter provides a comprehensive overview of established methodological tools, enriched by our practical experience. We develop the tasks involved in dataset development and offer insights into their effective management. Then, we provide more details about the implementation process which includes data collection, transformation, and quality evaluation.
  arXiv  Detail & Related papers  (2024-04-15T12:01:42Z)
• Any-point Trajectory Modeling for Policy Learning [64.23861308947852]
  We introduce Any-point Trajectory Modeling (ATM) to predict future trajectories of arbitrary points within a video frame. ATM outperforms strong video pre-training baselines by 80% on average. We show effective transfer learning of manipulation skills from human videos and videos from a different robot morphology.
  arXiv  Detail & Related papers  (2023-12-28T23:34:43Z)
• Towards A Unified Agent with Foundation Models [18.558328028366816]
  We investigate how to embed and leverage such abilities in Reinforcement Learning (RL) agents. We design a framework that uses language as the core reasoning tool, exploring how this enables an agent to tackle a series of fundamental RL challenges. We demonstrate substantial performance improvements over baselines in exploration efficiency and ability to reuse data from offline datasets.
  arXiv  Detail & Related papers  (2023-07-18T22:37:30Z)
• On Efficient Training of Large-Scale Deep Learning Models: A Literature Review [90.87691246153612]
  The field of deep learning has witnessed significant progress, particularly in computer vision (CV), natural language processing (NLP), and speech. The use of large-scale models trained on vast amounts of data holds immense promise for practical applications. With the increasing demands on computational capacity, a comprehensive summarization on acceleration techniques of training deep learning models is still much anticipated.
  arXiv  Detail & Related papers  (2023-04-07T11:13:23Z)
• A Vision for Semantically Enriched Data Science [19.604667287258724]
  Key areas such as utilizing domain knowledge and data semantics are areas where we have seen little automation. We envision how leveraging "semantic" understanding and reasoning on data in combination with novel tools for data science automation can help with consistent and explainable data augmentation and transformation.
  arXiv  Detail & Related papers  (2023-03-02T16:03:12Z)
• Data-driven Approaches to Surrogate Machine Learning Model Development [3.2734466030053175]
  We demonstrate the adaption of three established methods to the field of surrogate machine learning model development. These methods are data augmentation, custom loss functions and transfer learning. We see a significant improvement in model performance through the combination of all three techniques.
  arXiv  Detail & Related papers  (2022-10-06T01:30:11Z)
• BERT WEAVER: Using WEight AVERaging to enable lifelong learning for transformer-based models in biomedical semantic search engines [49.75878234192369]
  We present WEAVER, a simple, yet efficient post-processing method that infuses old knowledge into the new model. We show that applying WEAVER in a sequential manner results in similar word embedding distributions as doing a combined training on all data at once.
  arXiv  Detail & Related papers  (2022-02-21T10:34:41Z)
• Understanding the World Through Action [91.3755431537592]
  I will argue that a general, principled, and powerful framework for utilizing unlabeled data can be derived from reinforcement learning. I will discuss how such a procedure is more closely aligned with potential downstream tasks.
  arXiv  Detail & Related papers  (2021-10-24T22:33:52Z)
• What Matters in Learning from Offline Human Demonstrations for Robot Manipulation [64.43440450794495]
  We conduct an extensive study of six offline learning algorithms for robot manipulation. Our study analyzes the most critical challenges when learning from offline human data. We highlight opportunities for learning from human datasets.
  arXiv  Detail & Related papers  (2021-08-06T20:48:30Z)
• Efficient Deep Learning: A Survey on Making Deep Learning Models Smaller, Faster, and Better [0.0]
  With the progressive improvements in deep learning models, their number of parameters, latency, resources required to train, etc. have increased significantly. We present and motivate the problem of efficiency in deep learning, followed by a thorough survey of the five core areas of model efficiency. We believe this is the first comprehensive survey in the efficient deep learning space that covers the landscape of model efficiency from modeling techniques to hardware support.
  arXiv  Detail & Related papers  (2021-06-16T17:31:38Z)
• Visual Imitation Made Easy [102.36509665008732]
  We present an alternate interface for imitation that simplifies the data collection process while allowing for easy transfer to robots. We use commercially available reacher-grabber assistive tools both as a data collection device and as the robot's end-effector. We experimentally evaluate on two challenging tasks: non-prehensile pushing and prehensile stacking, with 1000 diverse demonstrations for each task.
  arXiv  Detail & Related papers  (2020-08-11T17:58:50Z)

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.