Research Papers

Getting from Generative AI to Trustworthy AI: What LLMs might learn from Cyc

Doug Lenat, Gary Marcus

Generative AI, the most popular current approach to AI, consists of large language models (LLMs) that are trained to produce outputs that are plausible, but not necessarily correct. Although their abilities are often uncanny, they are lacking in aspects of reasoning, leading LLMs to be less than completely trustworthy. Furthermore, their results tend to be both unpredictable and uninterpretable. We lay out 16 desiderata for future AI, and discuss an alternative approach to AI which could theoretically address many of the limitations associated with current approaches: AI educated with curated pieces of explicit knowledge and rules of thumb, enabling an inference engine to automatically deduce the logical entailments of all that knowledge. Even long arguments produced this way can be both trustworthy and interpretable, since the full step-by-step line of reasoning is always available, and for each step the provenance of the knowledge used can be documented and audited. There is however a catch: if the logical language is expressive enough to fully represent the meaning of anything we can say in English, then the inference engine runs much too slowly. That's why symbolic AI systems typically settle for some fast but much less expressive logic, such as knowledge graphs. We describe how one AI system, Cyc, has developed ways to overcome that tradeoff and is able to reason in higher order logic in real time. We suggest that any trustworthy general AI will need to hybridize the approaches, the LLM approach and more formal approach, and lay out a path to realizing that dream.

Despite progress in the field, significant parts of current XAI research are still not on solid conceptual, ethical, or methodological grounds. Unfortunately, these unfounded parts are not on the decline but continue to grow. Many explanation techniques are still proposed without clarifying their purpose. Instead, they are advertised with ever more fancy-looking heatmaps or only seemingly relevant benchmarks. Moreover, explanation techniques are motivated with questionable goals, such as building trust, or rely on strong assumptions about the 'concepts' that deep learning algorithms learn. In this paper, we highlight and discuss these and other misconceptions in current XAI research. We also suggest steps to make XAI a more substantive area of research.

Recently, there has been a growing demand for the deployment of Explainable Artificial Intelligence (XAI) algorithms in real-world applications. However, traditional XAI methods typically suffer from a high computational complexity problem, which discourages the deployment of real-time systems to meet the time-demanding requirements of real-world scenarios. Although many approaches have been proposed to improve the efficiency of XAI methods, a comprehensive understanding of the achievements and challenges is still needed. To this end, in this paper we provide a review of efficient XAI. Specifically, we categorize existing techniques of XAI acceleration into efficient non-amortized and efficient amortized methods. The efficient non-amortized methods focus on data-centric or model-centric acceleration upon each individual instance. In contrast, amortized methods focus on learning a unified distribution of model explanations, following the predictive, generative, or reinforcement frameworks, to rapidly derive multiple model explanations. We also analyze the limitations of an efficient XAI pipeline from the perspectives of the training phase, the deployment phase, and the use scenarios. Finally, we summarize the challenges of deploying XAI acceleration methods to real-world scenarios, overcoming the trade-off between faithfulness and efficiency, and the selection of different acceleration methods.

Disentangled Explanations of Neural Network Predictions by Finding Relevant Subspaces

Pattarawat Chormai, Jan Herrmann, Klaus-Robert Müller +1

Explainable AI aims to overcome the black-box nature of complex ML models like neural networks by generating explanations for their predictions. Explanations often take the form of a heatmap identifying input features (e.g. pixels) that are relevant to the model's decision. These explanations, however, entangle the potentially multiple factors that enter into the overall complex decision strategy. We propose to disentangle explanations by extracting at some intermediate layer of a neural network, subspaces that capture the multiple and distinct activation patterns (e.g. visual concepts) that are relevant to the prediction. To automatically extract these subspaces, we propose two new analyses, extending principles found in PCA or ICA to explanations. These novel analyses, which we call principal relevant component analysis (PRCA) and disentangled relevant subspace analysis (DRSA), maximize relevance instead of e.g. variance or kurtosis. This allows for a much stronger focus of the analysis on what the ML model actually uses for predicting, ignoring activations or concepts to which the model is invariant. Our approach is general enough to work alongside common attribution techniques such as Shapley Value, Integrated Gradients, or LRP. Our proposed methods show to be practically useful and compare favorably to the state of the art as demonstrated on benchmarks and three use cases.

Knowledge-Grounded Self-Rationalization via Extractive and Natural Language Explanations

Bodhisattwa Prasad Majumder, Oana-Maria Camburu, Thomas Lukasiewicz +1

Models that generate extractive rationales (i.e., subsets of features) or natural language explanations (NLEs) for their predictions are important for explainable AI. While an extractive rationale provides a quick view of the features most responsible for a prediction, an NLE allows for a comprehensive description of the decision-making process behind a prediction. However, current models that generate the best extractive rationales or NLEs often fall behind the state-of-the-art (SOTA) in terms of task performance. In this work, we bridge this gap by introducing RExC, a self-rationalizing framework that grounds its predictions and two complementary types of explanations (NLEs and extractive rationales) in background knowledge. Our framework improves over previous methods by: (i) reaching SOTA task performance while also providing explanations, (ii) providing two types of explanations, while existing models usually provide only one type, and (iii) beating by a large margin the previous SOTA in terms of quality of both types of explanations. Furthermore, a perturbation analysis in RExC shows a high degree of association between explanations and predictions, a necessary property of faithful explanations.

Despite significant advancements in AI-driven educational systems and ongoing calls for responsible AI for education, several critical issues remain unresolved -- acting as the elephant in the room within AI in education, learning analytics, educational data mining, learning sciences, and educational psychology communities. This critical analysis identifies and examines nine persistent challenges that continue to undermine the fairness, transparency, and effectiveness of current AI methods and applications in education. These include: (1) the lack of clarity around what AI for education truly means -- often ignoring the distinct purposes, strengths, and limitations of different AI families -- and the trend of equating it with domain-agnostic, company-driven large language models; (2) the widespread neglect of essential learning processes such as motivation, emotion, and (meta)cognition in AI-driven learner modelling and their contextual nature; (3) limited integration of domain knowledge and lack of stakeholder involvement in AI design and development; (4) continued use of non-sequential machine learning models on temporal educational data; (5) misuse of non-sequential metrics to evaluate sequential models; (6) use of unreliable explainable AI methods to provide explanations for black-box models; (7) ignoring ethical guidelines in addressing data inconsistencies during model training; (8) use of mainstream AI methods for pattern discovery and learning analytics without systematic benchmarking; and (9) overemphasis on global prescriptions while overlooking localised, student-specific recommendations. Supported by theoretical and empirical research, we demonstrate how hybrid AI methods -- specifically neural-symbolic AI -- can address the elephant in the room and serve as the foundation for responsible, trustworthy AI systems in education.

Revisiting the Performance-Explainability Trade-Off in Explainable Artificial Intelligence (XAI)

Barnaby Crook, Maximilian Schlüter, Timo Speith

Within the field of Requirements Engineering (RE), the increasing significance of Explainable Artificial Intelligence (XAI) in aligning AI-supported systems with user needs, societal expectations, and regulatory standards has garnered recognition. In general, explainability has emerged as an important non-functional requirement that impacts system quality. However, the supposed trade-off between explainability and performance challenges the presumed positive influence of explainability. If meeting the requirement of explainability entails a reduction in system performance, then careful consideration must be given to which of these quality aspects takes precedence and how to compromise between them. In this paper, we critically examine the alleged trade-off. We argue that it is best approached in a nuanced way that incorporates resource availability, domain characteristics, and considerations of risk. By providing a foundation for future research and best practices, this work aims to advance the field of RE for AI.

The interpretability of ML models is important, but it is not clear what it amounts to. So far, most philosophers have discussed the lack of interpretability of black-box models such as neural networks, and methods such as explainable AI that aim to make these models more transparent. The goal of this paper is to clarify the nature of interpretability by focussing on the other end of the 'interpretability spectrum'. The reasons why some models, linear models and decision trees, are highly interpretable will be examined, and also how more general models, MARS and GAM, retain some degree of interpretability. I find that while there is heterogeneity in how we gain interpretability, what interpretability is in particular cases can be explicated in a clear manner.

Uncertainty Quantification 360: A Holistic Toolkit for Quantifying and Communicating the Uncertainty of AI

Soumya Ghosh, Q. Vera Liao, Karthikeyan Natesan Ramamurthy +4

In this paper, we describe an open source Python toolkit named Uncertainty Quantification 360 (UQ360) for the uncertainty quantification of AI models. The goal of this toolkit is twofold: first, to provide a broad range of capabilities to streamline as well as foster the common practices of quantifying, evaluating, improving, and communicating uncertainty in the AI application development lifecycle; second, to encourage further exploration of UQ's connections to other pillars of trustworthy AI such as fairness and transparency through the dissemination of latest research and education materials. Beyond the Python package (\url{https://github.com/IBM/UQ360}), we have developed an interactive experience (\url{http://uq360.mybluemix.net}) and guidance materials as educational tools to aid researchers and developers in producing and communicating high-quality uncertainties in an effective manner.

Companies regularly spend millions of dollars producing electronically-stored documents in legal matters. Recently, parties on both sides of the 'legal aisle' are accepting the use of machine learning techniques like text classification to cull massive volumes of data and to identify responsive documents for use in these matters. While text classification is regularly used to reduce the discovery costs in legal matters, it also faces a peculiar perception challenge: amongst lawyers, this technology is sometimes looked upon as a "black box", little information provided for attorneys to understand why documents are classified as responsive. In recent years, a group of AI and ML researchers have been actively researching Explainable AI, in which actions or decisions are human understandable. In legal document review scenarios, a document can be identified as responsive, if one or more of its text snippets are deemed responsive. In these scenarios, if text classification can be used to locate these snippets, then attorneys could easily evaluate the model's classification decision. When deployed with defined and explainable results, text classification can drastically enhance overall quality and speed of the review process by reducing the review time. Moreover, explainable predictive coding provides lawyers with greater confidence in the results of that supervised learning task. This paper describes a framework for explainable text classification as a valuable tool in legal services: for enhancing the quality and efficiency of legal document review and for assisting in locating responsive snippets within responsive documents. This framework has been implemented in our legal analytics product, which has been used in hundreds of legal matters. We also report our experimental results using the data from an actual legal matter that used this type of document review.

Kandinsky Patterns

Heimo Mueller, Andreas Holzinger

Kandinsky Figures and Kandinsky Patterns are mathematically describable, simple self-contained hence controllable test data sets for the development, validation and training of explainability in artificial intelligence. Whilst Kandinsky Patterns have these computationally manageable properties, they are at the same time easily distinguishable from human observers. Consequently, controlled patterns can be described by both humans and computers. We define a Kandinsky Pattern as a set of Kandinsky Figures, where for each figure an "infallible authority" defines that the figure belongs to the Kandinsky Pattern. With this simple principle we build training and validation data sets for automatic interpretability and context learning. In this paper we describe the basic idea and some underlying principles of Kandinsky Patterns and provide a Github repository to invite the international machine learning research community to a challenge to experiment with our Kandinsky Patterns to expand and thus make progress in the field of explainable AI and to contribute to the upcoming field of explainability and causability.

Parkinson's disease (PD), the second most prevalent neurodegenerative disorder worldwide, frequently presents with early-stage speech impairments. Recent advancements in Artificial Intelligence (AI), particularly deep learning (DL), have significantly enhanced PD diagnosis through the analysis of speech data. Nevertheless, the progress of research is restricted by the limited availability of publicly accessible speech-based PD datasets, primarily due to privacy concerns. The goal of this systematic review is to explore the current landscape of speech-based DL approaches for PD classification, based on 33 scientific works published between January 2020 and March 2024. We discuss their available resources, capabilities, and potential limitations, and issues related to bias, explainability, and privacy. Furthermore, this review provides an overview of publicly accessible speech-based datasets and open-source material for PD. The DL approaches identified are categorized into end-to-end (E2E) learning, transfer learning (TL), and deep acoustic feature extraction (DAFE). Among E2E approaches, Convolutional Neural Networks (CNNs) are prevalent, though Transformers are increasingly popular. E2E approaches face challenges such as limited data and computational resources, especially with Transformers. TL addresses these issues by providing more robust PD diagnosis and better generalizability across languages. DAFE aims to improve the explainability and interpretability of results by examining the specific effects of deep features on both other DL approaches and more traditional machine learning (ML) methods. However, it often underperforms compared to E2E and TL approaches.