Exploration with Principles for Diverse AI Supervision

• URL: http://arxiv.org/abs/2310.08899v2
• Date: Thu, 23 Nov 2023 06:08:59 GMT
• Title: Exploration with Principles for Diverse AI Supervision
• Authors: Hao Liu, Matei Zaharia, Pieter Abbeel
• Abstract summary: Training large transformers using next-token prediction has given rise to groundbreaking advancements in AI. While this generative AI approach has produced impressive results, it heavily leans on human supervision. This strong reliance on human oversight poses a significant hurdle to the advancement of AI innovation. We propose a novel paradigm termed Exploratory AI (EAI) aimed at autonomously generating high-quality training data.
• Score: 88.61687950039662
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Training large transformers using next-token prediction has given rise to groundbreaking advancements in AI. While this generative AI approach has produced impressive results, it heavily leans on human supervision. Even state-of-the-art AI models like ChatGPT depend on fine-tuning through human demonstrations, demanding extensive human input and domain expertise. This strong reliance on human oversight poses a significant hurdle to the advancement of AI innovation. To address this limitation, we propose a novel paradigm termed Exploratory AI (EAI) aimed at autonomously generating high-quality training data. Drawing inspiration from unsupervised reinforcement learning (RL) pretraining, EAI achieves exploration within the natural language space. We accomplish this by harnessing large language models to assess the novelty of generated content. Our approach employs two key components: an actor that generates novel content following exploration principles and a critic that evaluates the generated content, offering critiques to guide the actor. Empirical evaluations demonstrate that EAI significantly boosts model performance on complex reasoning tasks, addressing the limitations of human-intensive supervision.

Related papers

• To Err Is AI! Debugging as an Intervention to Facilitate Appropriate Reliance on AI Systems [11.690126756498223]
  Vision for optimal human-AI collaboration requires 'appropriate reliance' of humans on AI systems. In practice, the performance disparity of machine learning models on out-of-distribution data makes dataset-specific performance feedback unreliable.
  arXiv  Detail & Related papers  (2024-09-22T09:43:27Z)
• Measuring Human Contribution in AI-Assisted Content Generation [68.03658922067487]
  This study raises the research question of measuring human contribution in AI-assisted content generation. By calculating mutual information between human input and AI-assisted output relative to self-information of AI-assisted output, we quantify the proportional information contribution of humans in content generation.
  arXiv  Detail & Related papers  (2024-08-27T05:56:04Z)
• Visions of a Discipline: Analyzing Introductory AI Courses on YouTube [11.209406323898019]
  We analyze the 20 most watched introductory AI courses on YouTube. Introductory AI courses do not meaningfully engage with ethical or societal challenges of AI. We recommend that introductory AI courses should highlight ethical challenges of AI to present a more balanced perspective.
  arXiv  Detail & Related papers  (2024-05-31T01:48:42Z)
• Generative Artificial Intelligence: A Systematic Review and Applications [7.729155237285151]
  This paper documents the systematic review and analysis of recent advancements and techniques in Generative AI. The major impact that generative AI has made to date, has been in language generation with the development of large language models. The paper ends with a discussion of Responsible AI principles, and the necessary ethical considerations for the sustainability and growth of these generative models.
  arXiv  Detail & Related papers  (2024-05-17T18:03:59Z)
• A call for embodied AI [1.7544885995294304]
  We propose Embodied AI as the next fundamental step in the pursuit of Artificial General Intelligence. By broadening the scope of Embodied AI, we introduce a theoretical framework based on cognitive architectures. This framework is aligned with Friston's active inference principle, offering a comprehensive approach to EAI development.
  arXiv  Detail & Related papers  (2024-02-06T09:11:20Z)
• Generative AI in Writing Research Papers: A New Type of Algorithmic Bias and Uncertainty in Scholarly Work [0.38850145898707145]
  Large language models (LLMs) and generative AI tools present challenges in identifying and addressing biases. generative AI tools are susceptible to goal misgeneralization, hallucinations, and adversarial attacks such as red teaming prompts. We find that incorporating generative AI in the process of writing research manuscripts introduces a new type of context-induced algorithmic bias.
  arXiv  Detail & Related papers  (2023-12-04T04:05:04Z)
• Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision [84.31474052176343]
  Recent AI-assistant agents, such as ChatGPT, rely on supervised fine-tuning (SFT) with human annotations and reinforcement learning from human feedback to align the output with human intentions. This dependence can significantly constrain the true potential of AI-assistant agents due to the high cost of obtaining human supervision. We propose a novel approach called SELF-ALIGN, which combines principle-driven reasoning and the generative power of LLMs for the self-alignment of AI agents with minimal human supervision.
  arXiv  Detail & Related papers  (2023-05-04T17:59:28Z)
• BO-Muse: A human expert and AI teaming framework for accelerated experimental design [58.61002520273518]
  Our algorithm lets the human expert take the lead in the experimental process. We show that our algorithm converges sub-linearly, at a rate faster than the AI or human alone.
  arXiv  Detail & Related papers  (2023-03-03T02:56:05Z)
• AI Maintenance: A Robustness Perspective [91.28724422822003]
  We introduce highlighted robustness challenges in the AI lifecycle and motivate AI maintenance by making analogies to car maintenance. We propose an AI model inspection framework to detect and mitigate robustness risks. Our proposal for AI maintenance facilitates robustness assessment, status tracking, risk scanning, model hardening, and regulation throughout the AI lifecycle.
  arXiv  Detail & Related papers  (2023-01-08T15:02:38Z)
• The Role of AI in Drug Discovery: Challenges, Opportunities, and Strategies [97.5153823429076]
  The benefits, challenges and drawbacks of AI in this field are reviewed. The use of data augmentation, explainable AI, and the integration of AI with traditional experimental methods are also discussed.
  arXiv  Detail & Related papers  (2022-12-08T23:23:39Z)

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.