arXiv subjects

Leilani H. Gilpin

Publications and source records attributed to Leilani H. Gilpin.

At least 19 recordsLinked to original sources

arXiv2026

"I didn't know how to read a map, but now I can": TouchingSpace, an Audio-Haptic Map for Blind and Low-Vision Readers

Accessible map systems either make a layout explorable by hand or convey information through speech; few combine both to support pre-travel spatial understanding for blind and low-vision (BLV) people. We present TouchingSpace: a system that retrieves map data for an outdoor place and renders its surroundings as bounded regions at fixed trackpad positions. During exploration, users receive audio and haptic feedback and can ask a conversational agent open-ended questions. We conducted a user study with fourteen BLV participants who explored a place using TouchingSpace and reflected on the experience. We found participants used sound and vibration to locate places and speech to identify and describe them; the bounded surface supported discovery, revision, and spatial checks by hand; they expected this awareness to support future travel. TouchingSpace demonstrates how a laptop trackpad can support self-directed spatial exploration. These findings suggest accessible AI maps should ground conversation on bounded, user-controlled spatial surfaces.

cs.HC↗

arXiv2026

From Anonymous Shapes to Named Places: A Tool for Braille and Place-Semantic Annotation of Tactile Maps

On a 3D-printed tactile map, a building felt under the finger is an anonymous shape: touch alone cannot tell which footprint is which, and a spoken description cannot reliably point to one shape at one place. We present a web-based tool that lets a sighted helper click to add on-shape Braille labels to an already-generated map model, downstream of the geometry generator so that whoever knows the reader and the local Braille standard does the labeling. The tool offers click-based OpenStreetMap matching, hand-editable abbreviation that shrinks a name to fit a footprint, and print-safe dot geometry with a review step that catches anomalies before printing. We demonstrate it on five printed maps of different place types, from a downtown core to a college campus and a small dining mall. In formative sessions in which ten BLV readers compared an unlabeled print with an annotated one, four read Braille fluently, so we treat Braille as one output among several rather than the only one. The tool's core is the link between coordinates, geometry, and a place's semantics, which can drive an audio readout or a non-Braille code. The tool is available at https://leolee7.github.io/Annotate_Braille/.

cs.HC↗

arXiv2026

Know Your Limits : On the Faithfulness of LLMs as Solvers and Autoformalizers in Legal Reasoning

Large Language Models (LLMs) achieve strong performance on reasoning tasks, but whether this reflects faithful logical inference or heuristic approximation remains unclear. We study this question in legal entailment by comparing three paradigms, including pure LLM classification, LLM-based Formal Reasoning, and solver-based Formal Reasoning using the Z3 SMT solver, on a re-annotated subset of ContractNLI across five LLMs. Our re-annotation reveals a systematic and measurable gap between pragmatic legal interpretation and strict formal entailment, where a substantial proportion of legally sound inferences are not formally grounded without additional unstated assumptions. While introducing formal structure improves accuracy, with LLM-based Formal Reasoning achieving the highest benchmark performance, we show that this gain does not imply faithful reasoning. We identify three recurring failure modes: scope laundering, where LLMs report solver-inconsistent classifications without executing the underlying formal reasoning, producing conclusions that appear logically grounded but are not; implicit constraint blindness, where LLMs overlook logical constraints present in formal representations; and program synthesis failures, where LLMs generate incorrect Z3 code despite structured prompting. Critically, scope laundering persists across all models, raising serious concerns about the faithfulness of LLM-based formal reasoning as a proxy for symbolic execution. These results reveal a fundamental gap between benchmark accuracy and logical faithfulness.

cs.AI↗

arXiv2026

Guaranteed Optimal Compositional Explanations for Neurons

Compositional explanations are a family of methods that aim to describe the spatial alignment between neurons' receptive field activations and concepts through logical rules, 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 assumptions related to the structure of the combinations and beam search to restrict the state 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 over the entire state space spanned by the adopted assumptions. 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 in a time comparable to exhaustive beam search. Using this framework, we demonstrate that 10-40% of explanations previously 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.

cs.AI↗

arXiv2026

Bridging Legal Interpretation and Formal Logic: Faithfulness, Assumption, and the Future of AI Legal Reasoning

The growing adoption of large language models in legal practice brings both significant promise and serious risk. Legal professionals stand to benefit from AI that can reason over contracts, draft documents, and analyze sources at scale, yet the high-stakes nature of legal work demands a level of rigor that current AI systems do not provide. The central problem is not simply that LLMs hallucinate facts and references; it is that they systematically draw inferences that go beyond what the source text actually supports, presenting assumption-laden conclusions as if they were logically grounded. This proposal presents a neuro-symbolic approach to legal AI that combines the expressive power of large language models with the rigor of formal verification, aiming to make AI-assisted legal reasoning both capable and trustworthy, thus reducing the burden of manual verification without sacrificing the accountability that legal practice demands.

cs.AI↗

arXiv2026

Touching Space: Accessible Map Exploration Through Conversational Audio-Haptic Interaction

Most existing assistive navigation tools focus on providing real-time guidance for Blind and Low-Vision (BLV) people, but few support building a holistic spatial understanding of unfamiliar environments before travel. Such cognitive map construction (e.g., knowing that a fountain is south of a tower and west of a hotel) is important for pre-travel planning, yet remains underexplored in prior work. To address this gap, we present Touching Space, an end-to-end system that retrieves map data for a target place and loads it into a frontend interface for exploration. The system combines haptic and audio feedback: users explore spatial layouts through touch and ask spoken questions to a conversational agent during exploration. Touching Space contributes a conversational interface that supports BLV users in building cognitive maps on commodity hardware.

cs.HC↗

arXiv2026

Learning to Draw ASCII Improves Spatial Reasoning in Language Models

When faced with complex spatial problems, humans naturally sketch layouts to organize their thinking, and the act of drawing further sharpens their understanding. In this work, we ask whether a similar principle holds for Large Language Models (LLMs): can learning to construct explicit visual layouts from spatial descriptions instill genuine spatial understanding? We introduce Text2Space, a dataset that pairs natural language descriptions with ground-truth ASCII grid layouts and spatial QA pairs, enabling us to separate failures in constructing spatial representations from failures in reasoning over them. We adopt ASCII because it is human-readable, operates entirely within the token space of language models, and encodes spatial relations in a structurally verifiable form. Our evaluation reveals a pronounced "Read-Write Asymmetry": LLMs interpret ASCII representations effectively but struggle to produce them from text, and these construction errors propagate to incorrect answers downstream. To address this limitation, we train models on layout construction (Text$\rightarrow$ASCII) and find that it significantly improves spatial reasoning from text alone, even without producing any ASCII at inference time. Combining construction with comprehension training further amplifies these gains. Crucially, these improvements transfer to three external spatial reasoning benchmarks, demonstrating that, much as sketching sharpens human spatial thinking, learning to construct explicit layouts instills spatial understanding that generalizes beyond the training format.

cs.AI↗

arXiv2025

Open Vocabulary Compositional Explanations for Neuron Alignment

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.

cs.CV↗

arXiv2025

Follow My Lead: Logical Fallacy Classification with Knowledge-Augmented LLMs

Large Language Models (LLMs) suffer from critical reasoning gaps, including a tendency to hallucinate and poor accuracy in classifying logical fallacies. This limitation stems from their default System 1 processing, which is fast and intuitive, whereas reliable reasoning requires the deliberate, effortful System 2 approach (Kahneman, 2011; Li et al., 2025). Since full System 2 training is often prohibitively expensive, we explore a low-cost, instruction-based intervention to bridge this gap. Our methodology introduces a novel stepwise instruction dataset that decomposes fallacy classification into a series of atomic procedural steps (simple binary questions). We further augment this with a final verification step where models consult a relational knowledge graph of related fallacies. This procedural, rule-based intervention yields a significant improvement in LLM logical fallacy classification. Crucially, the approach also provides enhanced transparency into the LLMs' decision-making, highlighting a practical pathway for Neuro-symbolic architectures to address LLM reasoning deficits.

cs.AI↗

arXiv2025

VFSI: Validity First Spatial Intelligence for Constraint-Guided Traffic Diffusion

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.

cs.CV↗

arXiv2025

Slug Mobile: Test-Bench for RL Testing

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.

cs.RO↗

arXiv2024

Right this way: Can VLMs Guide Us to See More to Answer Questions?

In question-answering scenarios, humans can assess whether the available information is sufficient and seek additional information if necessary, rather than providing a forced answer. In contrast, Vision Language Models (VLMs) typically generate direct, one-shot responses without evaluating the sufficiency of the information. To investigate this gap, we identify a critical and challenging task in the Visual Question Answering (VQA) scenario: can VLMs indicate how to adjust an image when the visual information is insufficient to answer a question? This capability is especially valuable for assisting visually impaired individuals who often need guidance to capture images correctly. To evaluate this capability of current VLMs, we introduce a human-labeled dataset as a benchmark for this task. Additionally, we present an automated framework that generates synthetic training data by simulating ``where to know'' scenarios. Our empirical results show significant performance improvements in mainstream VLMs when fine-tuned with this synthetic data. This study demonstrates the potential to narrow the gap between information assessment and acquisition in VLMs, bringing their performance closer to humans.

cs.CV↗

arXiv2023

Towards a fuller understanding of neurons with Clustered Compositional Explanations

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.

cs.LG↗

arXiv2023

Can Large Language Models Explain Themselves? A Study of LLM-Generated Self-Explanations

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.

cs.CL↗

arXiv2023

Convolutional Neural Network Model for Diabetic Retinopathy Feature Extraction and Classification

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.

eess.IV↗

arXiv2023

Anticipatory Thinking Challenges in Open Worlds: Risk Management

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.

cs.AI↗

arXiv2022

"Explanation" is Not a Technical Term: The Problem of Ambiguity in XAI

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.

cs.HC↗

arXiv2019

Explaining Explanations: An Overview of Interpretability of Machine Learning

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.

cs.AI↗