Explainable Artificial Intelligence (XAI)

Derniers papiers

• Real-Time Trustworthiness Scoring for LLM Structured Outputs and Data Extraction

  Hui Wen Goh, Jonas Mueller · 20 mars 2026

  Structured Outputs from current LLMs exhibit sporadic errors, hindering enterprise AI efforts from realizing their immense potential. We present CONSTRUCT, a method to score the trustworthiness of LLM Structured Outputs in real-time, such that lower-scoring outputs are more likely to contain errors.…

• Foundations and Architectures of Artificial Intelligence for Motor Insurance

  Teerapong Panboonyuen · 20 mars 2026

  This handbook presents a systematic treatment of the foundations and architectures of artificial intelligence for motor insurance, grounded in large-scale real-world deployment. It formalizes a vertically integrated AI paradigm that unifies perception, multimodal reasoning, and production infrastruc…

• A Structured Nonparametric Framework for Nonlinear Accelerated Failure Time Models (KAN-AFT)

  Mebin Jose, Jisha Francis, Sudheesh Kumar Kattumannil · 20 mars 2026

  Accelerated failure time (AFT) models provide a direct and interpretable time-scale description of covariate effects in lifetime data analysis, but classical formulations rely on linear predictors and are therefore limited in their ability to represent nonlinear relationships. Moreover, in heterogen…

• Clinically Meaningful Explainability for NeuroAI: An ethical, technical, and clinical perspective

  Laura Schopp, Ambra DImperio, Jalal Etesami, Marcello Ienca · 20 mars 2026

  While explainable AI (XAI) is often heralded as a means to enhance transparency and trustworthiness in closed-loop neurotechnology for psychiatric and neurological conditions, its real-world prevalence remains low. Moreover, empirical evidence suggests that the type of explanations provided by curre…

• Automated Explanation Selection for Scientific Discovery

  Ashlin Iser · 20 mars 2026

  Automated reasoning is a key technology in the young but rapidly growing field of Explainable Artificial Intelligence (XAI). Explanability helps build trust in artificial intelligence systems beyond their mere predictive accuracy and robustness. In this paper, we propose a cycle of scientific discov…

• WASD: Locating Critical Neurons as Sufficient Conditions for Explaining and Controlling LLM Behavior

  Haonan Yu, Junhao Liu, Zhenyu Yan, Haoran Lin, Xin Zhang · 20 mars 2026

  Precise behavioral control of large language models (LLMs) is critical for complex applications. However, existing methods often incur high training costs, lack natural language controllability, or compromise semantic coherence. To bridge this gap, we propose WASD (unWeaving Actionable Sufficient Di…

• Fundamental Limits of Neural Network Sparsification: Evidence from Catastrophic Interpretability Collapse

  Dip Roy, Rajiv Misra, Sanjay Kumar Singh · 20 mars 2026

  Extreme neural network sparsification (90% activation reduction) presents a critical challenge for mechanistic interpretability: understanding whether interpretable features survive aggressive compression. This work investigates feature survival under severe capacity constraints in hybrid Variationa…

• AgentDS Technical Report: Benchmarking the Future of Human-AI Collaboration in Domain-Specific Data Science

  An Luo, Jin Du, Xun Xian, Robert Specht, Fangqiao Tian, Ganghua Wang, Xuan Bi, Charles Fleming, Ashish Kundu, Jayanth Srinivasa, Mingyi Hong, Rui Zhang, Tianxi Li, Galin Jones, Jie Ding · 20 mars 2026

  Data science plays a critical role in transforming complex data into actionable insights across numerous domains. Recent developments in large language models (LLMs) and artificial intelligence (AI) agents have significantly automated data science workflow. However, it remains unclear to what extent…

• MedForge: Interpretable Medical Deepfake Detection via Forgery-aware Reasoning

  Zhihui Chen, Kai He, Qingyuan Lei, Bin Pu, Jian Zhang, Yuling Xu, Mengling Feng · 20 mars 2026

  Text-guided image editors can now manipulate authentic medical scans with high fidelity, enabling lesion implantation/removal that threatens clinical trust and safety. Existing defenses are inadequate for healthcare. Medical detectors are largely black-box, while MLLM-based explainers are typically …

• Discovering What You Can Control: Interventional Boundary Discovery for Reinforcement Learning

  Jiaxin Liu · 20 mars 2026

  Selecting relevant state dimensions in the presence of confounded distractors is a causal identification problem: observational statistics alone cannot reliably distinguish dimensions that correlate with actions from those that actions cause. We formalize this as discovering the agent's Causal Spher…

• Towards more holistic interpretability: A lightweight disentangled Concept Bottleneck Model

  Gaoxiang Huang, Songning Lai, Yutao Yue · 20 mars 2026

  Concept Bottleneck Models (CBMs) enhance interpretability by predicting human-understandable concepts as intermediate representations. However, existing CBMs often suffer from input-to-concept mapping bias and limited controllability, which restricts their practical utility and undermines the reliab…

• AGRI-Fidelity: Evaluating the Reliability of Listenable Explanations for Poultry Disease Detection

  Sindhuja Madabushi, Arda Dogan, Jonathan Liu, Dian Chen, Dong S. Ha, Sook Shin, Sam H. Noh, Jin-Hee Cho · 20 mars 2026

  Existing XAI metrics measure faithfulness for a single model, ignoring model multiplicity where near-optimal classifiers rely on different or spurious acoustic cues. In noisy farm environments, stationary artifacts such as ventilation noise can produce explanations that are faithful yet unreliable, …

• Quantitative Introspection in Language Models: Tracking Internal States Across Conversation

  Nicolas Martorell · 20 mars 2026

  Tracking the internal states of large language models across conversations is important for safety, interpretability, and model welfare, yet current methods are limited. Linear probes and other white-box methods compress high-dimensional representations imperfectly and are harder to apply with incre…

• WeNLEX: Weakly Supervised Natural Language Explanations for Multilabel Chest X-ray Classification

  Isabel Rio-Torto, Jaime S. Cardoso, Lu\'is F. Teixeira · 20 mars 2026

  Natural language explanations provide an inherently human-understandable way to explain black-box models, closely reflecting how radiologists convey their diagnoses in textual reports. Most works explicitly supervise the explanation generation process using datasets annotated with explanations. Thus…

• REAL: Regression-Aware Reinforcement Learning for LLM-as-a-Judge

  Yasi Zhang, Tianyu Chen, Mingyuan Zhou, Oscar Leong, Ying Nian Wu, Michal Lukasik · 19 mars 2026

  Large language models (LLMs) are increasingly deployed as automated evaluators that assign numeric scores to model outputs, a paradigm known as LLM-as-a-Judge. However, standard Reinforcement Learning (RL) methods typically rely on binary rewards (e.g., 0-1 accuracy), thereby ignoring the ordinal st…

• I Know What I Don't Know: Latent Posterior Factor Models for Multi-Evidence Probabilistic Reasoning

  Aliyu Agboola Alege · 19 mars 2026

  Real-world decision-making, from tax compliance assessment to medical diagnosis, requires aggregating multiple noisy and potentially contradictory evidence sources. Existing approaches either lack explicit uncertainty quantification (neural aggregation methods) or rely on manually engineered discret…

• Explanations Go Linear: Post-hoc Explainability for Tabular Data with Interpretable Meta-Encoding

  Simone Piaggesi, Riccardo Guidotti, Fosca Giannotti, Dino Pedreschi · 19 mars 2026

  Post-hoc explainability is essential for understanding black-box machine learning models. Surrogate-based techniques are widely used for local and global model-agnostic explanations but have significant limitations. Local surrogates capture non-linearities but are computationally expensive and sensi…

• A Progressive Visual-Logic-Aligned Framework for Ride-Hailing Adjudication

  Weiming Wu, Zi-Jian Cheng, Jie Meng, Peng Zhen, Shan Huang, Qun Li, Guobin Wu, Lan-Zhe Guo · 19 mars 2026

  The efficient adjudication of responsibility disputes is pivotal for maintaining marketplace fairness. However, the exponential surge in ride-hailing volume renders manual review intractable, while conventional automated methods lack the reasoning transparency required for quasi-judicial decisions. …

• Informative Semi-Factuals for XAI: The Elaborated Explanations that People Prefer

  Saugat Aryal, Mark T. Keane · 19 mars 2026

  Recently, in eXplainable AI (XAI), $\textit{even if}$ explanations -- so-called semi-factuals -- have emerged as a popular strategy that explains how a predicted outcome $\textit{can remain the same}$ even when certain input-features are altered. For example, in the commonly-used banking app scenari…

• Knowing What You Cannot Explain: Learning to Reject Low-Quality Explanations

  Luca Stradiotti, Dario Pesenti, Stefano Teso, Jesse Davis · 19 mars 2026

  Learning to Reject (LtR) frameworks allow ML models to abstain from uncertain predictions and promote user trust. However, since current LtR strategies focus solely on predictive performance, they completely neglect explanation quality. Low-quality explanations -- whether they inaccurately reflect t…

• I Know What I Don't Know: Latent Posterior Factor Models for Multi-Evidence Probabilistic Reasoning

  Aliyu Agboola Alege · 19 mars 2026

  Real-world decision-making, from tax compliance assessment to medical diagnosis, requires aggregating multiple noisy and potentially contradictory evidence sources. Existing approaches either lack explicit uncertainty quantification (neural aggregation methods) or rely on manually engineered discret…

• SCE-LITE-HQ: Smooth visual counterfactual explanations with generative foundation models

  Ahmed Zeid, Sidney Bender · 19 mars 2026

  Modern neural networks achieve strong performance but remain difficult to interpret in high-dimensional visual domains. Counterfactual explanations (CFEs) provide a principled approach to interpreting black-box predictions by identifying minimal input changes that alter model outputs. However, exist…

• Noise-Response Calibration: A Causal Intervention Protocol for LLM-Judges

  Maxim Khomiakov, Jes Frellsen · 19 mars 2026

  Large language models (LLMs) are increasingly used as automated judges and synthetic labelers, especially in low-label settings. Yet these systems are stochastic and often overconfident, which makes deployment decisions difficult when external ground truth is limited. We propose a practical calibrat…

• ReLMXEL: Adaptive RL-Based Memory Controller with Explainable Energy and Latency Optimization

  Panuganti Chirag Sai, Gandholi Sarat, R. Raghunatha Sarma, Venkata Kalyan Tavva, Naveen M · 19 mars 2026

  Reducing latency and energy consumption is critical to improving the efficiency of memory systems in modern computing. This work introduces ReLMXEL (Reinforcement Learning for Memory Controller with Explainable Energy and Latency Optimization), a explainable multi-agent online reinforcement learning…

• Discovering Decoupled Functional Modules in Large Language Models

  Yanke Yu, Jin Li, Ying Sun, Ping Li, Zhefeng Wang, Yi Zheng · 19 mars 2026

  Understanding the internal functional organization of Large Language Models (LLMs) is crucial for improving their trustworthiness and performance. However, how LLMs organize different functions into modules remains highly unexplored. To bridge this gap, we formulate a functional module discovery pro…