Research Papers

As artificial intelligence increasingly drives critical decisions, the ability to genuinely explain how neural networks make predictions is essential for trust. Yet, most current explanation methods offer post-hoc rationalizations rather than guaranteeing a true reflection of the model's reasoning. We introduce the notion of explanatory alignment, a requirement that explanations directly construct predictions rather than rationalize them. To achieve this in complex data domains, we present Pointwise-interpretable Networks (PiNets), a pseudo-linear architecture that forms linear models instance-wise. Evaluated on image classification and segmentation tasks, PiNets demonstrate that their explanations are deeply faithful across four criteria: meaningfulness, alignment, robustness, and sufficiency (MARS). Our contributions pave the way for promising avenues: by reconciling the predictive power of deep learning with the interpretability of linear models, PiNets provide a principled foundation for trustworthy AI and data-driven scientific discovery.

Sentiment analysis focuses on identifying the emotional polarity expressed in textual data, typically categorized as positive, negative, or neutral. Hate speech detection, on the other hand, aims to recognize content that incites violence, discrimination, or hostility toward individuals or groups based on attributes such as race, gender, sexual orientation, or religion. Both tasks play a critical role in online content moderation by enabling the detection and mitigation of harmful or offensive material, thereby contributing to safer digital environments. In this study, we examine the performance of three transformer-based models: BERT-base-multilingual-cased, RoBERTa-base, and XLM-RoBERTa-base with the first eight layers frozen, for multilingual sentiment analysis and hate speech detection. The evaluation is conducted across five languages: English, Korean, Japanese, Chinese, and French. The models are compared using standard performance metrics, including accuracy, precision, recall, and F1-score. To enhance model interpretability and provide deeper insight into prediction behavior, we integrate the Local Interpretable Model-agnostic Explanations (LIME) framework, which highlights the contribution of individual words to the models decisions. By combining state-of-the-art transformer architectures with explainability techniques, this work aims to improve both the effectiveness and transparency of multilingual sentiment analysis and hate speech detection systems.

Large Language Models (LLMs) are increasingly evaluated with input attribution methods, yet comparing such explanations remains challenging. Existing soft-perturbation faithfulness metrics, such as Soft-NC and Soft-NS, can conflate attribution quality with the number of words retained during perturbation: attribution methods with larger average scores may keep more words and therefore obtain inflated scores. To address this issue, we propose $π$-Soft-NC and $π$-Soft-NS, an evaluation framework that compares attribution methods under the same expected retaining probability, thus controlling the number of retained words. We further introduce Grad-ELLM, a gradient-based attribution method tailored to autoregressive decoder-only LLMs, which combines gradient-derived channel importance with attention-derived token importance at each decoding step. Experiments on classification and open-generation tasks with Llama and Mistral show that Grad-ELLM achieves strong comprehensiveness-oriented faithfulness under $π$-Soft-NC, while there is no dominant method under $π$-Soft-NS. Our evaluation metric serves as a rigorous framework to compare XAI methods for LLMs, which will support progress in the field.

As generative AI systems become integrated into real-world applications, organizations increasingly need to be able to understand and interpret their behavior. In particular, decision-makers need to understand what causes generative AI systems to exhibit specific output characteristics. Within this general topic, this paper examines a key question: what is it about the input -- the prompt -- that causes an LLM-based generative AI system to produce output that exhibits specific characteristics, such as toxicity, negative sentiment, or political bias. To examine this question, we adapt a common technique from the Explainable AI literature: counterfactual explanations. We explain why traditional counterfactual explanations cannot be applied directly to generative AI systems, due to several differences in how generative AI systems function. We then propose a flexible framework that adapts counterfactual explanations to non-deterministic, generative AI systems in scenarios where downstream classifiers can reveal key characteristics of their outputs. Based on this framework, we introduce an algorithm for generating prompt-counterfactual explanations (PCEs). Finally, we demonstrate the production of counterfactual explanations for generative AI systems with three case studies, examining different output characteristics (viz., political leaning, toxicity, and sentiment). The case studies further show that PCEs can streamline prompt engineering to suppress undesirable output characteristics and can enhance red-teaming efforts to uncover additional prompts that elicit undesirable outputs. Ultimately, this work lays a foundation for prompt-focused interpretability in generative AI: a capability that will become indispensable as these models are entrusted with higher-stakes tasks and subject to emerging regulatory requirements for transparency and accountability.

Despite recent advances in machine learning and explainable AI, a gap remains in personalized preventive healthcare: predictions, interventions, and recommendations should be both understandable and verifiable for all stakeholders in the healthcare sector. We present a demonstration of how prototype-based learning can address these needs. Our proposed framework, ProtoPal, features both front- and back-end modes; it achieves superior quantitative performance while also providing an intuitive presentation of interventions and their simulated outcomes.

iFlip: Iterative Feedback-driven Counterfactual Example Refinement

Yilong Wang, Qianli Wang, Nils Feldhus

Counterfactual examples are minimal edits to an input that alter a model's prediction. They are widely employed in explainable AI to probe model behavior and in natural language processing (NLP) to augment training data. However, generating valid counterfactuals with large language models (LLMs) remains challenging, as existing single-pass methods often fail to induce reliable label changes, neglecting LLMs' self-correction capabilities. To explore this untapped potential, we propose iFlip, an iterative refinement approach that leverages three types of feedback, including model confidence, feature attribution, and natural language. Our results show that iFlip achieves an average 57.8% higher validity than the five state-of-the-art baselines, as measured by the label flipping rate. The user study further corroborates that iFlip outperforms baselines in completeness, overall satisfaction, and feasibility. In addition, ablation studies demonstrate that three components are paramount for iFlip to generate valid counterfactuals: leveraging an appropriate number of iterations, pointing to highly attributed words, and early stopping. Finally, counterfactuals generated by iFlip enable effective counterfactual data augmentation, substantially improving model performance and robustness.

Standard simulations of the Iterated Prisoners Dilemma (IPD) operate in deterministic, noise-free environments, producing strategies that may be theoretically optimal but fragile when confronted with real-world uncertainty. This paper addresses two critical gaps in evolutionary game theory research: (1) the absence of realistic environmental stressors during strategy evolution, and (2) the Interpretability Gap, where evolved genetic strategies remain opaque binary sequences devoid of semantic meaning. We introduce a novel framework combining stochastic environmental perturbations (God Mode) with Large Language Model (LLM)-based behavioral profiling to transform evolved genotypes into interpretable character archetypes. Our experiments demonstrate that strategies evolved under chaotic conditions exhibit superior resilience and present distinct behavioral phenotypes, ranging from Ruthless Capitalists to Diplomatic Enforcers. These phenotypes are readily classified by LLMs but remain nearly impossible to interpret through manual genome inspection alone. This work bridges evolutionary computation with explainable AI and provides a template for automated agent characterization in multi-agent systems.

Theory of Mind for Explainable Human-Robot Interaction

Marie S. Bauer, Julia Gachot, Matthias Kerzel +2

Within the context of human-robot interaction (HRI), Theory of Mind (ToM) is intended to serve as a user-friendly backend to the interface of robotic systems, enabling robots to infer and respond to human mental states. When integrated into robots, ToM allows them to adapt their internal models to users' behaviors, enhancing the interpretability and predictability of their actions. Similarly, Explainable Artificial Intelligence (XAI) aims to make AI systems transparent and interpretable, allowing humans to understand and interact with them effectively. Since ToM in HRI serves related purposes, we propose to consider ToM as a form of XAI and evaluate it through the eValuation XAI (VXAI) framework and its seven desiderata. This paper identifies a critical gap in the application of ToM within HRI, as existing methods rarely assess the extent to which explanations correspond to the robot's actual internal reasoning. To address this limitation, we propose to integrate ToM within XAI frameworks. By embedding ToM principles inside XAI, we argue for a shift in perspective, as current XAI research focuses predominantly on the AI system itself and often lacks user-centered explanations. Incorporating ToM would enable a change in focus, prioritizing the user's informational needs and perspective.

Interpretable Gallbladder Ultrasound Diagnosis: A Lightweight Web-Mobile Software Platform with Real-Time XAI

Fuyad Hasan Bhoyan, Prashanta Sarker, Parsia Noor Ethila +3

Early and accurate detection of gallbladder diseases is crucial, yet ultrasound interpretation is challenging. To address this, an AI-driven diagnostic software integrates our hybrid deep learning model MobResTaNet to classify ten categories, nine gallbladder disease types and normal directly from ultrasound images. The system delivers interpretable, real-time predictions via Explainable AI (XAI) visualizations, supporting transparent clinical decision-making. It achieves up to 99.85% accuracy with only 2.24M parameters. Deployed as web and mobile applications using HTML, CSS, JavaScript, Bootstrap, and Flutter, the software provides efficient, accessible, and trustworthy diagnostic support at the point of care

The increasing use of Machine Learning (ML) in sensitive domains such as healthcare, finance, and public policy has raised concerns about the transparency of automated decisions. Explainable AI (XAI) addresses this by clarifying how models generate predictions, yet most methods demand technical expertise, limiting their value for novices. This gap is especially critical in no-code ML platforms, which seek to democratize AI but rarely include explainability. We present a human-centered XAI module in DashAI, an open-source no-code ML platform. The module integrates three complementary techniques, which are Partial Dependence Plots (PDP), Permutation Feature Importance (PFI), and KernelSHAP, into DashAI's workflow for tabular classification. A user study (N = 20; ML novices and experts) evaluated usability and the impact of explanations. Results show: (i) high task success ($\geq80\%$) across all explainability tasks; (ii) novices rated explanations as useful, accurate, and trustworthy on the Explanation Satisfaction Scale (ESS, Cronbach's $α$ = 0.74, a measure of internal consistency), while experts were more critical of sufficiency and completeness; and (iii) explanations improved perceived predictability and confidence on the Trust in Automation scale (TiA, $α$ = 0.60), with novices showing higher trust than experts. These findings highlight a central challenge for XAI in no-code ML, making explanations both accessible to novices and sufficiently detailed for experts.

Automated clinical ICD-10 coding is a high-impact healthcare task requiring a balance between coverage, precision, and safety. While neural approaches achieve strong performance, they suffer from hallucination-generating invalid or unsupported codes-posing unacceptable risks in safety-critical clinical settings. Rule-based systems eliminate hallucination but lack scalability and coverage due to manual knowledge base (KB) curation. We present Hybrid-Code v2, a neuro-symbolic framework that achieves zero Type-I hallucination by construction while maintaining competitive coverage and precision. The system integrates neural candidate generation with a symbolic KB verification layer that enforces validity constraints through multi-layer verification, including format, evidence grounding, negation detection, temporal consistency, and exclusion rules. In addition, we introduce an automated KB expansion mechanism that extracts and validates coding patterns from unlabeled clinical text, addressing the scalability limitations of rule-based systems. Evaluated on the MIMIC-III dataset against ClinicalBERT, BioBERT, rule-based systems, and GPT-4, Hybrid-Code v2 achieves 85% coverage, 92% precision, and 0% Type-I hallucination, outperforming rule-based systems by +40% coverage while eliminating hallucination observed in neural baselines (6-18%). The proposed architecture provides a formal safety guarantee for syntactic validity while preserving strong empirical performance. These results demonstrate that neuro-symbolic verification can enforce safety constraints in neural medical AI systems without sacrificing effectiveness, offering a generalizable design pattern for deploying trustworthy AI in safety-critical domains.

Explainable artificial intelligence (XAI) reveals how explanatory variables relate to a response variable, yet communicating XAI outputs to laypersons remains difficult, limiting trust in AI-based predictions. Large language models (LLMs) can translate technical explanations into accessible narratives, but iterative refinement of XAI explanations by an autonomous LLM agent remains unexplored. This study proposes an agentic XAI framework that combines SHapley Additive exPlanations (SHAP) with iterative refinement by a multimodal LLM and tests it as an agricultural recommendation system on rice yield data from 28 fields in Japan. From a SHAP result, the agent explored additional analyses across 11 refinement rounds (Rounds 0-10). Crop scientists (n = 12) and LLM judges (n = 14) scored every round on seven criteria: Specificity, Clarity, Conciseness, Practicality, Contextual Relevance, Cost Consideration, and Crop Science Credibility. Both groups found that refinement raised the average score by 30-33% over Round 0, peaking at Rounds 3-4, after which quality declined, below the starting point for crop scientists. Refinement therefore requires strategic early stopping, which challenges assumptions of monotonic improvement. Criterion-level trajectories indicate a bias-variance trade-off. Early rounds lacked Specificity (bias), whereas excessive iteration eroded Conciseness and raised Cost Consideration through ungrounded economic reasoning (variance). The LLM judges overscored every criterion by 1.4-2.3 points but largely preserved the experts' ranking of rounds (Spearman $ρ$ = 0.58-0.90), so screened LLM judges can flag the quality peak despite unreliable absolute scores. Trustworthy agentic XAI also needs expert-anchored screening of LLM judges and transparent, verifiable refinement records.