Ultra Strong Machine Learning: Teaching Humans Active Learning Strategies via Automated AI Explanations

• URL: http://arxiv.org/abs/2509.00961v1
• Date: Sun, 31 Aug 2025 19:04:31 GMT
• Title: Ultra Strong Machine Learning: Teaching Humans Active Learning Strategies via Automated AI Explanations
• Authors: Lun Ai, Johannes Langer, Ute Schmid, Stephen Muggleton,
• Abstract summary: We present LENS, a neuro-symbolic method that combines symbolic program synthesis with large language models (LLMs) to automate the explanation of machine-learned logic programs in natural language.<n>LENS addresses a key limitation of prior USML approaches by replacing hand-crafted explanation templates with scalable automated generation.<n>Our results show no significant human performance improvements, suggesting that comprehensive LLM responses may overwhelm users for simpler problems rather than providing learning support.
• Score: 2.530461847957792
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Ultra Strong Machine Learning (USML) refers to symbolic learning systems that not only improve their own performance but can also teach their acquired knowledge to quantifiably improve human performance. In this work, we present LENS (Logic Programming Explanation via Neural Summarisation), a neuro-symbolic method that combines symbolic program synthesis with large language models (LLMs) to automate the explanation of machine-learned logic programs in natural language. LENS addresses a key limitation of prior USML approaches by replacing hand-crafted explanation templates with scalable automated generation. Through systematic evaluation using multiple LLM judges and human validation, we demonstrate that LENS generates superior explanations compared to direct LLM prompting and hand-crafted templates. To investigate whether LENS can teach transferable active learning strategies, we carried out a human learning experiment across three related domains. Our results show no significant human performance improvements, suggesting that comprehensive LLM responses may overwhelm users for simpler problems rather than providing learning support. Our work provides a solid foundation for building effective USML systems to support human learning. The source code is available on: https://github.com/lun-ai/LENS.git.

Related papers

• Leveraging Large Language Models for Explainable Activity Recognition in Smart Homes: A Critical Evaluation [0.29998889086656577]
  XAI has been applied to sensor-based Activities of Daily Living (ADLs) recognition in smart homes.<n>This paper investigates potential approaches to combine XAI and Large Language Models (LLMs) for sensor-based ADL recognition.
  arXiv  Detail & Related papers  (2025-03-20T18:23:03Z)
• Large Language Models are Interpretable Learners [53.56735770834617]
  In this paper, we show a combination of Large Language Models (LLMs) and symbolic programs can bridge the gap between expressiveness and interpretability. The pretrained LLM with natural language prompts provides a massive set of interpretable modules that can transform raw input into natural language concepts. As the knowledge learned by LSP is a combination of natural language descriptions and symbolic rules, it is easily transferable to humans (interpretable) and other LLMs.
  arXiv  Detail & Related papers  (2024-06-25T02:18:15Z)
• Verbalized Machine Learning: Revisiting Machine Learning with Language Models [63.10391314749408]
  We introduce the framework of verbalized machine learning (VML)<n>VML constrains the parameter space to be human-interpretable natural language.<n>We empirically verify the effectiveness of VML, and hope that VML can serve as a stepping stone to stronger interpretability.
  arXiv  Detail & Related papers  (2024-06-06T17:59:56Z)
• Generative AI-in-the-loop: Integrating LLMs and GPTs into the Next Generation Networks [11.509880721677156]
  Large language models (LLMs) have recently emerged, demonstrating near-human-level performance in cognitive tasks. We propose the concept of "generative AI-in-the-loop" We believe that combining LLMs and ML models allows both to leverage their respective capabilities and achieve better results than either model alone.
  arXiv  Detail & Related papers  (2024-06-06T17:25:07Z)
• From Summary to Action: Enhancing Large Language Models for Complex Tasks with Open World APIs [62.496139001509114]
  We introduce a novel tool invocation pipeline designed to control massive real-world APIs. This pipeline mirrors the human task-solving process, addressing complicated real-life user queries. Empirical evaluations of our Sum2Act pipeline on the ToolBench benchmark show significant performance improvements.
  arXiv  Detail & Related papers  (2024-02-28T08:42:23Z)
• LLM A*: Human in the Loop Large Language Models Enabled A* Search for Robotics [2.9053316583692146]
  This research focuses on how Large Language Models (LLMs) can help with (path) planning for mobile embodied agents such as robots.<n>A novel framework named LLM A*, aims to leverage the commonsense of LLMs, and the utility-optimal A* is proposed to facilitate few-shot near-optimal path planning.<n>This approach takes human feedback on board and renders the entire planning process transparent (akin to a white box') to humans.
  arXiv  Detail & Related papers  (2023-12-04T10:37:58Z)
• Accelerating Reinforcement Learning of Robotic Manipulations via Feedback from Large Language Models [21.052532074815765]
  We introduce the Lafite-RL (Language agent feedback interactive Reinforcement Learning) framework. It enables RL agents to learn robotic tasks efficiently by taking advantage of Large Language Models' timely feedback. It outperforms the baseline in terms of both learning efficiency and success rate.
  arXiv  Detail & Related papers  (2023-11-04T11:21:38Z)
• Democratizing Reasoning Ability: Tailored Learning from Large Language Model [97.4921006089966]
  We propose a tailored learning approach to distill such reasoning ability to smaller LMs. We exploit the potential of LLM as a reasoning teacher by building an interactive multi-round learning paradigm. To exploit the reasoning potential of the smaller LM, we propose self-reflection learning to motivate the student to learn from self-made mistakes.
  arXiv  Detail & Related papers  (2023-10-20T07:50:10Z)
• Language models are weak learners [71.33837923104808]
  We show that prompt-based large language models can operate effectively as weak learners. We incorporate these models into a boosting approach, which can leverage the knowledge within the model to outperform traditional tree-based boosting. Results illustrate the potential for prompt-based LLMs to function not just as few-shot learners themselves, but as components of larger machine learning pipelines.
  arXiv  Detail & Related papers  (2023-06-25T02:39:19Z)
• Self-directed Machine Learning [86.3709575146414]
  In education science, self-directed learning has been shown to be more effective than passive teacher-guided learning. We introduce the principal concept of Self-directed Machine Learning (SDML) and propose a framework for SDML. Our proposed SDML process benefits from self task selection, self data selection, self model selection, self optimization strategy selection and self evaluation metric selection.
  arXiv  Detail & Related papers  (2022-01-04T18:32:06Z)

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.