Automated Capability Discovery via Model Self-Exploration

• URL: http://arxiv.org/abs/2502.07577v2
• Date: Wed, 12 Feb 2025 16:25:44 GMT
• Title: Automated Capability Discovery via Model Self-Exploration
• Authors: Cong Lu, Shengran Hu, Jeff Clune,
• Abstract summary: We introduce Automated Capability Discovery (ACD), a framework that designates one foundation model as a scientist to propose open-ended tasks. ACD automatically uncovers both surprising capabilities and failures in the subject model. We demonstrate ACD across a range of foundation models, showing that it automatically reveals thousands of capabilities that would be challenging for any single team to uncover.
• Score: 5.404186221463082
• License:
• Abstract: Foundation models have become general-purpose assistants, exhibiting diverse capabilities across numerous domains through training on web-scale data. It remains challenging to precisely characterize even a fraction of the full spectrum of capabilities and potential risks in any new model. Existing evaluation approaches often require significant human effort, and it is taking increasing effort to design ever harder challenges for more capable models. We introduce Automated Capability Discovery (ACD), a framework that designates one foundation model as a scientist to systematically propose open-ended tasks probing the abilities of a subject model (potentially itself). By combining frontier models with ideas from the field of open-endedness, ACD automatically and systematically uncovers both surprising capabilities and failures in the subject model. We demonstrate ACD across a range of foundation models (including the GPT, Claude, and Llama series), showing that it automatically reveals thousands of capabilities that would be challenging for any single team to uncover. We further validate our method's automated scoring with extensive human surveys, observing high agreement between model-generated and human evaluations. By leveraging foundation models' ability to both create tasks and self-evaluate, ACD is a significant step toward scalable, automated evaluation of novel AI systems. All code and evaluation logs are open-sourced at https://github.com/conglu1997/ACD.

Related papers

• Unsupervised Model Diagnosis [49.36194740479798]
  This paper proposes Unsupervised Model Diagnosis (UMO) to produce semantic counterfactual explanations without any user guidance. Our approach identifies and visualizes changes in semantics, and then matches these changes to attributes from wide-ranging text sources.
  arXiv  Detail & Related papers  (2024-10-08T17:59:03Z)
• ReVLA: Reverting Visual Domain Limitation of Robotic Foundation Models [55.07988373824348]
  We study the visual generalization capabilities of three existing robotic foundation models. Our study shows that the existing models do not exhibit robustness to visual out-of-domain scenarios. We propose a gradual backbone reversal approach founded on model merging.
  arXiv  Detail & Related papers  (2024-09-23T17:47:59Z)
• AIDE: An Automatic Data Engine for Object Detection in Autonomous Driving [68.73885845181242]
  We propose an Automatic Data Engine (AIDE) that automatically identifies issues, efficiently curates data, improves the model through auto-labeling, and verifies the model through generation of diverse scenarios. We further establish a benchmark for open-world detection on AV datasets to comprehensively evaluate various learning paradigms, demonstrating our method's superior performance at a reduced cost.
  arXiv  Detail & Related papers  (2024-03-26T04:27:56Z)
• Forging Vision Foundation Models for Autonomous Driving: Challenges, Methodologies, and Opportunities [59.02391344178202]
  Vision foundation models (VFMs) serve as potent building blocks for a wide range of AI applications. The scarcity of comprehensive training data, the need for multi-sensor integration, and the diverse task-specific architectures pose significant obstacles to the development of VFMs. This paper delves into the critical challenge of forging VFMs tailored specifically for autonomous driving, while also outlining future directions.
  arXiv  Detail & Related papers  (2024-01-16T01:57:24Z)
• TrainerAgent: Customizable and Efficient Model Training through LLM-Powered Multi-Agent System [14.019244136838017]
  TrainerAgent is a multi-agent framework including Task, Data, Model and Server agents. These agents analyze user-defined tasks, input data, and requirements (e.g., accuracy, speed), optimizing them from both data and model perspectives to obtain satisfactory models, and finally deploy these models as online service. This research presents a significant advancement in achieving desired models with increased efficiency and quality as compared to traditional model development.
  arXiv  Detail & Related papers  (2023-11-11T17:39:24Z)
• 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)
• Fusing Models with Complementary Expertise [42.099743709292866]
  We consider the Fusion of Experts (FoE) problem of fusing outputs of expert models with complementary knowledge of the data distribution. Our method is applicable to both discriminative and generative tasks. We extend our method to the "frugal" setting where it is desired to reduce the number of expert model evaluations at test time.
  arXiv  Detail & Related papers  (2023-10-02T18:31:35Z)
• TaskMatrix.AI: Completing Tasks by Connecting Foundation Models with Millions of APIs [71.7495056818522]
  We introduce TaskMatrix.AI as a new AI ecosystem that connects foundation models with millions of APIs for task completion. We will present our vision of how to build such an ecosystem, explain each key component, and use study cases to illustrate both the feasibility of this vision and the main challenges we need to address next.
  arXiv  Detail & Related papers  (2023-03-29T03:30:38Z)
• Foundation models in brief: A historical, socio-technical focus [2.5991265608180396]
  Foundation models can be disruptive for future AI development by scaling up deep learning. Models achieve state-of-the-art performance on a variety of tasks in domains such as natural language processing and computer vision.
  arXiv  Detail & Related papers  (2022-12-17T22:11:33Z)

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.