Building Trustworthy NeuroSymbolic AI Systems: Consistency, Reliability,
Explainability, and Safety
- URL: http://arxiv.org/abs/2312.06798v1
- Date: Tue, 5 Dec 2023 06:13:55 GMT
- Title: Building Trustworthy NeuroSymbolic AI Systems: Consistency, Reliability,
Explainability, and Safety
- Authors: Manas Gaur, Amit Sheth
- Abstract summary: We present the CREST framework that shows how Consistency, Reliability, user-level Explainability, and Safety are built on NeuroSymbolic methods.
This article focuses on Large Language Models (LLMs) as the chosen AI system within the CREST framework.
- Score: 11.933469815219544
- License: http://creativecommons.org/licenses/by-sa/4.0/
- Abstract: Explainability and Safety engender Trust. These require a model to exhibit
consistency and reliability. To achieve these, it is necessary to use and
analyze data and knowledge with statistical and symbolic AI methods relevant to
the AI application - neither alone will do. Consequently, we argue and seek to
demonstrate that the NeuroSymbolic AI approach is better suited for making AI a
trusted AI system. We present the CREST framework that shows how Consistency,
Reliability, user-level Explainability, and Safety are built on NeuroSymbolic
methods that use data and knowledge to support requirements for critical
applications such as health and well-being. This article focuses on Large
Language Models (LLMs) as the chosen AI system within the CREST framework. LLMs
have garnered substantial attention from researchers due to their versatility
in handling a broad array of natural language processing (NLP) scenarios. For
example, ChatGPT and Google's MedPaLM have emerged as highly promising
platforms for providing information in general and health-related queries,
respectively. Nevertheless, these models remain black boxes despite
incorporating human feedback and instruction-guided tuning. For instance,
ChatGPT can generate unsafe responses despite instituting safety guardrails.
CREST presents a plausible approach harnessing procedural and graph-based
knowledge within a NeuroSymbolic framework to shed light on the challenges
associated with LLMs.
Related papers
- Converging Paradigms: The Synergy of Symbolic and Connectionist AI in LLM-Empowered Autonomous Agents [54.247747237176625]
Article explores the convergence of connectionist and symbolic artificial intelligence (AI)
Traditionally, connectionist AI focuses on neural networks, while symbolic AI emphasizes symbolic representation and logic.
Recent advancements in large language models (LLMs) highlight the potential of connectionist architectures in handling human language as a form of symbols.
arXiv Detail & Related papers (2024-07-11T14:00:53Z) - Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systems [88.80306881112313]
We will introduce and define a family of approaches to AI safety, which we will refer to as guaranteed safe (GS) AI.
The core feature of these approaches is that they aim to produce AI systems which are equipped with high-assurance quantitative safety guarantees.
We outline a number of approaches for creating each of these three core components, describe the main technical challenges, and suggest a number of potential solutions to them.
arXiv Detail & Related papers (2024-05-10T17:38:32Z) - Concept-Guided LLM Agents for Human-AI Safety Codesign [6.603483691167379]
Generative AI is increasingly important in software engineering, including safety engineering, where its use ensures that software does not cause harm to people.
It is crucial to develop more advanced and sophisticated approaches that can effectively address the complexities and safety concerns of software systems.
We present an efficient, hybrid strategy to leverage Large Language Models for safety analysis and Human-AI codesign.
arXiv Detail & Related papers (2024-04-03T11:37:01Z) - Machine Learning Robustness: A Primer [12.426425119438846]
The discussion begins with a detailed definition of robustness, portraying it as the ability of ML models to maintain stable performance across varied and unexpected environmental conditions.
The chapter delves into the factors that impede robustness, such as data bias, model complexity, and the pitfalls of underspecified ML pipelines.
The discussion progresses to explore amelioration strategies for bolstering robustness, starting with data-centric approaches like debiasing and augmentation.
arXiv Detail & Related papers (2024-04-01T03:49:42Z) - NeuralSentinel: Safeguarding Neural Network Reliability and
Trustworthiness [0.0]
We present NeuralSentinel (NS), a tool able to validate the reliability and trustworthiness of AI models.
NS help non-expert staff increase their confidence in this new system by understanding the model decisions.
This tool was deployed and used in a Hackathon event to evaluate the reliability of a skin cancer image detector.
arXiv Detail & Related papers (2024-02-12T09:24:34Z) - The Role of Foundation Models in Neuro-Symbolic Learning and Reasoning [54.56905063752427]
Neuro-Symbolic AI (NeSy) holds promise to ensure the safe deployment of AI systems.
Existing pipelines that train the neural and symbolic components sequentially require extensive labelling.
New architecture, NeSyGPT, fine-tunes a vision-language foundation model to extract symbolic features from raw data.
arXiv Detail & Related papers (2024-02-02T20:33:14Z) - Representation Engineering: A Top-Down Approach to AI Transparency [132.0398250233924]
We identify and characterize the emerging area of representation engineering (RepE)
RepE places population-level representations, rather than neurons or circuits, at the center of analysis.
We showcase how these methods can provide traction on a wide range of safety-relevant problems.
arXiv Detail & Related papers (2023-10-02T17:59:07Z) - Requirements for Explainability and Acceptance of Artificial
Intelligence in Collaborative Work [0.0]
The present structured literature analysis examines the requirements for the explainability and acceptance of AI.
Results indicate that the two main groups of users are developers who require information about the internal operations of the model.
The acceptance of AI systems depends on information about the system's functions and performance, privacy and ethical considerations.
arXiv Detail & Related papers (2023-06-27T11:36:07Z) - Statistical Perspectives on Reliability of Artificial Intelligence
Systems [6.284088451820049]
We provide statistical perspectives on the reliability of AI systems.
We introduce a so-called SMART statistical framework for AI reliability research.
We discuss recent developments in modeling and analysis of AI reliability.
arXiv Detail & Related papers (2021-11-09T20:00:14Z) - Trustworthy AI [75.99046162669997]
Brittleness to minor adversarial changes in the input data, ability to explain the decisions, address the bias in their training data, are some of the most prominent limitations.
We propose the tutorial on Trustworthy AI to address six critical issues in enhancing user and public trust in AI systems.
arXiv Detail & Related papers (2020-11-02T20:04:18Z) - Neuro-symbolic Architectures for Context Understanding [59.899606495602406]
We propose the use of hybrid AI methodology as a framework for combining the strengths of data-driven and knowledge-driven approaches.
Specifically, we inherit the concept of neuro-symbolism as a way of using knowledge-bases to guide the learning progress of deep neural networks.
arXiv Detail & Related papers (2020-03-09T15:04:07Z)
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.