Leilani H. Gilpin

Leilani H. Gilpin, Andrew R. Paley, Mohammed A. Alam et al. · mit

There is broad agreement that Artificial Intelligence (AI) systems, particularly those using Machine Learning (ML), should be able to "explain" their behavior. Unfortunately, there is little agreement as to what constitutes an "explanation." This has caused a disconnect between the explanations that systems produce in service of explainable Artificial Intelligence (XAI) and those explanations that users and other audiences actually need, which should be defined by the full spectrum of functional roles, audiences, and capabilities for explanation. In this paper, we explore the features of explanations and how to use those features in evaluating their utility. We focus on the requirements for explanations defined by their functional role, the knowledge states of users who are trying to understand them, and the availability of the information needed to generate them. Further, we discuss the risk of XAI enabling trust in systems without establishing their trustworthiness and define a critical next step for the field of XAI to establish metrics to guide and ground the utility of system-generated explanations.

Shreyan Mitra, Leilani Gilpin · mit

Explanatory systems make machine learning models more transparent. However, they are often inconsistent. In order to quantify and isolate possible scenarios leading to this discrepancy, this paper compares two explanatory systems, SHAP and LIME, based on the correlation of their respective importance scores using 14 machine learning models (7 regression and 7 classification) and 4 tabular datasets (2 regression and 2 classification). We make two novel findings. Firstly, the magnitude of importance is not significant in explanation consistency. The correlations between SHAP and LIME importance scores for the most important features may or may not be more variable than the correlation between SHAP and LIME importance scores averaged across all features. Secondly, the similarity between SHAP and LIME importance scores cannot predict model accuracy. In the process of our research, we construct an open-source library, XAISuite, that unifies the process of training and explaining models. Finally, this paper contributes a generalized framework to better explain machine learning models and optimize their performance.

Priyesh Vakharia, Abigail Kufeldt, Max Meyers et al. · mit

Neurosymbolic approaches can add robustness to opaque neural systems by incorporating explainable symbolic representations. However, previous approaches have not used formal logic to contextualize queries to and validate outputs of large language models (LLMs). We propose \systemname{}, a novel neurosymbolic framework, to improve the robustness and reliability of LLMs in question-answering tasks. We provide \systemname{} with a domain-specific knowledge base, a logical reasoning system, and an integration to an existing LLM. This framework has two capabilities (1) context gathering: generating explainable and relevant context for a given query, and (2) validation: confirming and validating the factual accuracy of a statement in accordance with a knowledge base (KB). Our work opens a new area of neurosymbolic generative AI text validation and user personalization.

Cosmin Badea, Leilani Gilpin · mit

We propose an ontology of building decision-making systems, with the aim of establishing Meta-Decision-Making for Artificial Intelligence (AI), improving autonomy, and creating a framework to build metrics and benchmarks upon. To this end, we propose the three parts of Relevance, Representation, and Reasoning, and discuss their value in ensuring safety and mitigating risk in the context of third wave cognitive systems. Our nomenclature reflects the literature on decision-making, and our ontology allows researchers that adopt it to frame their work in relation to one or more of these parts.

Adam Amos-Binks, Dustin Dannenhauer, Leilani H. Gilpin · mit

Anticipatory thinking drives our ability to manage risk - identification and mitigation - in everyday life, from bringing an umbrella when it might rain to buying car insurance. As AI systems become part of everyday life, they too have begun to manage risk. Autonomous vehicles log millions of miles, StarCraft and Go agents have similar capabilities to humans, implicitly managing risks presented by their opponents. To further increase performance in these tasks, out-of-distribution evaluation can characterize a model's bias, what we view as a type of risk management. However, learning to identify and mitigate low-frequency, high-impact risks is at odds with the observational bias required to train machine learning models. StarCraft and Go are closed-world domains whose risks are known and mitigations well documented, ideal for learning through repetition. Adversarial filtering datasets provide difficult examples but are laborious to curate and static, both barriers to real-world risk management. Adversarial robustness focuses on model poisoning under the assumption there is an adversary with malicious intent, without considering naturally occurring adversarial examples. These methods are all important steps towards improving risk management but do so without considering open-worlds. We unify these open-world risk management challenges with two contributions. The first is our perception challenges, designed for agents with imperfect perceptions of their environment whose consequences have a high impact. Our second contribution are cognition challenges, designed for agents that must dynamically adjust their risk exposure as they identify new risks and learn new mitigations. Our goal with these challenges is to spur research into solutions that assess and improve the anticipatory thinking required by AI agents to manage risk in open-worlds and ultimately the real-world.

Shiyuan Huang, Siddarth Mamidanna, Shreedhar Jangam et al.

Large language models (LLMs) such as ChatGPT have demonstrated superior performance on a variety of natural language processing (NLP) tasks including sentiment analysis, mathematical reasoning and summarization. Furthermore, since these models are instruction-tuned on human conversations to produce "helpful" responses, they can and often will produce explanations along with the response, which we call self-explanations. For example, when analyzing the sentiment of a movie review, the model may output not only the positivity of the sentiment, but also an explanation (e.g., by listing the sentiment-laden words such as "fantastic" and "memorable" in the review). How good are these automatically generated self-explanations? In this paper, we investigate this question on the task of sentiment analysis and for feature attribution explanation, one of the most commonly studied settings in the interpretability literature (for pre-ChatGPT models). Specifically, we study different ways to elicit the self-explanations, evaluate their faithfulness on a set of evaluation metrics, and compare them to traditional explanation methods such as occlusion or LIME saliency maps. Through an extensive set of experiments, we find that ChatGPT's self-explanations perform on par with traditional ones, but are quite different from them according to various agreement metrics, meanwhile being much cheaper to produce (as they are generated along with the prediction). In addition, we identified several interesting characteristics of them, which prompt us to rethink many current model interpretability practices in the era of ChatGPT(-like) LLMs.

Biagio La Rosa, Leilani H. Gilpin, Roberto Capobianco

Compositional Explanations is a method for identifying logical formulas of concepts that approximate the neurons' behavior. However, these explanations are linked to the small spectrum of neuron activations (i.e., the highest ones) used to check the alignment, thus lacking completeness. In this paper, we propose a generalization, called Clustered Compositional Explanations, that combines Compositional Explanations with clustering and a novel search heuristic to approximate a broader spectrum of the neurons' behavior. We define and address the problems connected to the application of these methods to multiple ranges of activations, analyze the insights retrievable by using our algorithm, and propose desiderata qualities that can be used to study the explanations returned by different algorithms.

Sharan Subramanian, Leilani H. Gilpin

The application of Artificial Intelligence in the medical market brings up increasing concerns but aids in more timely diagnosis of silent progressing diseases like Diabetic Retinopathy. In order to diagnose Diabetic Retinopathy (DR), ophthalmologists use color fundus images, or pictures of the back of the retina, to identify small distinct features through a difficult and time-consuming process. Our work creates a novel CNN model and identifies the severity of DR through fundus image input. We classified 4 known DR features, including micro-aneurysms, cotton wools, exudates, and hemorrhages, through convolutional layers and were able to provide an accurate diagnostic without additional user input. The proposed model is more interpretable and robust to overfitting. We present initial results with a sensitivity of 97% and an accuracy of 71%. Our contribution is an interpretable model with similar accuracy to more complex models. With that, our model advances the field of DR detection and proves to be a key step towards AI-focused medical diagnosis.

Jonathan Wellington Morris, Vishrut Shah, Alex Besanceney et al.

Sim-to real gap in Reinforcement Learning is when a model trained in a simulator does not translate to the real world. This is a problem for Autonomous Vehicles (AVs) as vehicle dynamics can vary from simulation to reality, and also from vehicle to vehicle. Slug Mobile is a one tenth scale autonomous vehicle created to help address the sim-to-real gap for AVs by acting as a test-bench to develop models that can easily scale from one vehicle to another. In addition to traditional sensors found in other one tenth scale AVs, we have also included a Dynamic Vision Sensor so we can train Spiking Neural Networks running on neuromorphic hardware.

Shreyan Mitra, Leilani Gilpin

Explanatory systems make the behavior of machine learning models more transparent, but are often inconsistent. To quantify the differences between explanatory systems, this paper presents the Shreyan Distance, a novel metric based on the weighted difference between ranked feature importance lists produced by such systems. This paper uses the Shreyan Distance to compare two explanatory systems, SHAP and LIME, for both regression and classification learning tasks. Because we find that the average Shreyan Distance varies significantly between these two tasks, we conclude that consistency between explainers not only depends on inherent properties of the explainers themselves, but also the type of learning task. This paper further contributes the XAISuite library, which integrates the Shreyan distance algorithm into machine learning pipelines.

Biagio La Rosa, Leilani H. Gilpin

While neurons are the basic units of deep neural networks, it is still unclear what they learn and if their knowledge is aligned with that of humans. Compositional explanations aim to answer this question by describing the spatial alignment between neuron activations and concepts through logical rules. These logical descriptions are typically computed via a search over all possible concept combinations. Since computing the spatial alignment over the entire state space is computationally infeasible, the literature commonly adopts beam search to restrict the space. However, beam search cannot provide any theoretical guarantees of optimality, and it remains unclear how close current explanations are to the true optimum. In this theoretical paper, we address this gap by introducing the first framework for computing guaranteed optimal compositional explanations. Specifically, we propose: (i) a decomposition that identifies the factors influencing the spatial alignment, (ii) a heuristic to estimate the alignment at any stage of the search, and (iii) the first algorithm that can compute optimal compositional explanations within a feasible time. Using this framework, we analyze the differences between optimal and non-optimal explanations in the most popular settings for compositional explanations, the computer vision domain and Convolutional Neural Networks. In these settings, we demonstrate that 10-40 percent of explanations obtained with beam search are suboptimal when overlapping concepts are involved. Finally, we evaluate a beam-search variant guided by our proposed decomposition and heuristic, showing that it matches or improves runtime over prior methods while offering greater flexibility in hyperparameters and computational resources.

Biagio La Rosa, Leilani H. Gilpin

Neurons are the fundamental building blocks of deep neural networks, and their interconnections allow AI to achieve unprecedented results. Motivated by the goal of understanding how neurons encode information, compositional explanations leverage logical relationships between concepts to express the spatial alignment between neuron activations and human knowledge. However, these explanations rely on human-annotated datasets, restricting their applicability to specific domains and predefined concepts. This paper addresses this limitation by introducing a framework for the vision domain that allows users to probe neurons for arbitrary concepts and datasets. Specifically, the framework leverages masks generated by open vocabulary semantic segmentation to compute open vocabulary compositional explanations. The proposed framework consists of three steps: specifying arbitrary concepts, generating semantic segmentation masks using open vocabulary models, and deriving compositional explanations from these masks. The paper compares the proposed framework with previous methods for computing compositional explanations both in terms of quantitative metrics and human interpretability, analyzes the differences in explanations when shifting from human-annotated data to model-annotated data, and showcases the additional capabilities provided by the framework in terms of flexibility of the explanations with respect to the tasks and properties of interest.

Meenakshi Manikandan, Leilani Gilpin

This paper introduces Hill-ADAM. Hill-ADAM is an optimizer with its focus towards escaping local minima in prescribed loss landscapes to find the global minimum. Hill-ADAM escapes minima by deterministically exploring the state space. This eliminates uncertainty from random gradient updates in stochastic algorithms while seldom converging at the first minimum that visits. In the paper we first derive an analytical approximation of the ADAM Optimizer step size at a particular model state. From there define the primary condition determining ADAM limitations in escaping local minima. The proposed optimizer algorithm Hill-ADAM alternates between error minimization and maximization. It maximizes to escape the local minimum and minimizes again afterward. This alternation provides an overall exploration throughout the loss space. This allows the deduction of the global minimum's state. Hill-ADAM was tested with 5 loss functions and 12 amber-saturated to cooler-shade image color correction instances.

Kargi Chauhan, Leilani H. Gilpin

Modern diffusion models generate realistic traffic simulations but systematically violate physical constraints. In a large-scale evaluation of SceneDiffuser++, a state-of-the-art traffic simulator, we find that 50% of generated trajectories violate basic physical laws - vehicles collide, drive off roads, and spawn inside buildings. This reveals a fundamental limitation: current models treat physical validity as an emergent property rather than an architectural requirement. We propose Validity-First Spatial Intelligence (VFSI), which enforces constraints through energy-based guidance during diffusion sampling, without model retraining. By incorporating collision avoidance and kinematic constraints as energy functions, we guide the denoising process toward physically valid trajectories. Across 200 urban scenarios from the Waymo Open Motion Dataset, VFSI reduces collision rates by 67% (24.6% to 8.1%) and improves overall validity by 87% (50.3% to 94.2%), while simultaneously improving realism metrics (ADE: 1.34m to 1.21m). Our model-agnostic approach demonstrates that explicit constraint enforcement during inference is both necessary and sufficient for physically valid traffic simulation.

Jason R. Wilson, Leilani Gilpin, Irina Rabkina

There is a need for socially assistive robots (SARs) to provide transparency in their behavior by explaining their reasoning. Additionally, the reasoning and explanation should represent the user's preferences and goals. To work towards satisfying this need for interpretable reasoning and representations, we propose the robot uses Analogical Theory of Mind to infer what the user is trying to do and uses the Hint Engine to find an appropriate assistance based on what the user is trying to do. If the user is unsure or confused, the robot provides the user with an explanation, generated by the Explanation Synthesizer. The explanation helps the user understand what the robot inferred about the user's preferences and why the robot decided to provide the assistance it gave. A knowledge-driven approach provides transparency to reasoning about preferences, assistance, and explanations, thereby facilitating the incorporation of user feedback and allowing the robot to learn and adapt to the user.

Leilani H. Gilpin, Cecilia Testart, Nathaniel Fruchter et al.

There is a disconnect between explanatory artificial intelligence (XAI) methods and the types of explanations that are useful for and demanded by society (policy makers, government officials, etc.) Questions that experts in artificial intelligence (AI) ask opaque systems provide inside explanations, focused on debugging, reliability, and validation. These are different from those that society will ask of these systems to build trust and confidence in their decisions. Although explanatory AI systems can answer many questions that experts desire, they often don't explain why they made decisions in a way that is precise (true to the model) and understandable to humans. These outside explanations can be used to build trust, comply with regulatory and policy changes, and act as external validation. In this paper, we focus on XAI methods for deep neural networks (DNNs) because of DNNs' use in decision-making and inherent opacity. We explore the types of questions that explanatory DNN systems can answer and discuss challenges in building explanatory systems that provide outside explanations for societal requirements and benefit.

Leilani H. Gilpin, David Bau, Ben Z. Yuan et al.

There has recently been a surge of work in explanatory artificial intelligence (XAI). This research area tackles the important problem that complex machines and algorithms often cannot provide insights into their behavior and thought processes. XAI allows users and parts of the internal system to be more transparent, providing explanations of their decisions in some level of detail. These explanations are important to ensure algorithmic fairness, identify potential bias/problems in the training data, and to ensure that the algorithms perform as expected. However, explanations produced by these systems is neither standardized nor systematically assessed. In an effort to create best practices and identify open challenges, we provide our definition of explainability and show how it can be used to classify existing literature. We discuss why current approaches to explanatory methods especially for deep neural networks are insufficient. Finally, based on our survey, we conclude with suggested future research directions for explanatory artificial intelligence.