Explainable Artificial Intelligence (XAI)

Derniers papiers

• Explainable machine learning workflows for radio astronomical data processing

  S. Yatawatta, A. Ahmadi, B. Asabere, M. Iacobelli, N. Peters, M. Veldhuis · 18 mars 2026

  Radio astronomy relies heavily on efficient and accurate processing pipelines to deliver science ready data. With the increasing data flow of modern radio telescopes, manual configuration of such data processing pipelines is infeasible. Machine learning (ML) is already emerging as a viable solution …

• RetailBench: Evaluating Long-Horizon Autonomous Decision-Making and Strategy Stability of LLM Agents in Realistic Retail Environments

  Linghua Zhang, Jun Wang, Jingtong Wu, Zhisong Zhang · 18 mars 2026

  Large Language Model (LLM)-based agents have achieved notable success on short-horizon and highly structured tasks. However, their ability to maintain coherent decision-making over long horizons in realistic and dynamic environments remains an open challenge. We introduce RetailBench, a high-fidel…

• Understanding Moral Reasoning Trajectories in Large Language Models: Toward Probing-Based Explainability

  Fan Huang, Haewoon Kwak, Jisun An · 18 mars 2026

  Large language models (LLMs) increasingly participate in morally sensitive decision-making, yet how they organize ethical frameworks across reasoning steps remains underexplored. We introduce \textit{moral reasoning trajectories}, sequences of ethical framework invocations across intermediate reason…

• BenchPreS: A Benchmark for Context-Aware Personalized Preference Selectivity of Persistent-Memory LLMs

  Sangyeon Yoon, Sunkyoung Kim, Hyesoo Hong, Wonje Jeung, Yongil Kim, Wooseok Seo, Heuiyeen Yeen, Albert No · 18 mars 2026

  Large language models (LLMs) increasingly store user preferences in persistent memory to support personalization across interactions. However, in third-party communication settings governed by social and institutional norms, some user preferences may be inappropriate to apply. We introduce BenchPreS…

• Theoretical Foundations of Latent Posterior Factors: Formal Guarantees for Multi-Evidence Reasoning

  Aliyu Agboola Alege · 18 mars 2026

  We present a complete theoretical characterization of Latent Posterior Factors (LPF), a principled framework for aggregating multiple heterogeneous evidence items in probabilistic prediction tasks. Multi-evidence reasoning arises pervasively in high-stakes domains including healthcare diagnosis, fin…

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

  Aliyu Agboola Alege · 18 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…

• MAC: Multi-Agent Constitution Learning

  Rushil Thareja, Gautam Gupta, Francesco Pinto, Nils Lukas · 18 mars 2026

  Constitutional AI is a method to oversee and control LLMs based on a set of rules written in natural language. These rules are typically written by human experts, but could in principle be learned automatically given sufficient training data for the desired behavior. Existing LLM-based prompt optimi…

• Interpretative Interfaces: Designing for AI-Mediated Reading Practices and the Knowledge Commons

  Gabrielle Benabdallah · 18 mars 2026

  Explainable AI (XAI) interfaces seek to make large language models more transparent, yet explanation alone does not produce understanding. Explaining a system's behavior is not the same as being able to engage with it, to probe and interpret its operations through direct manipulation. This distincti…

• NextMem: Towards Latent Factual Memory for LLM-based Agents

  Zeyu Zhang, Rui Li, Xiaoyan Zhao, Yang Zhang, Wenjie Wang, Xu Chen, Tat-Seng Chua · 18 mars 2026

  Memory is critical for LLM-based agents to preserve past observations for future decision-making, where factual memory serves as its foundational part. However, existing approaches to constructing factual memory face several limitations. Textual methods impose heavy context and indexing burdens, whi…

• Steering Frozen LLMs: Adaptive Social Alignment via Online Prompt Routing

  Zeyu Zhang, Xiangxiang Dai, Ziyi Han, Xutong Liu, John C. S. Lui · 18 mars 2026

  Large language models (LLMs) are typically governed by post-training alignment (e.g., RLHF or DPO), which yields a largely static policy during deployment and inference. However, real-world safety is a full-lifecycle problem: static defenses degrade against evolving jailbreak behaviors, and fixed we…

• Hypothesis Class Determines Explanation: Why Accurate Models Disagree on Feature Attribution

  Thackshanaramana B · 18 mars 2026

  The assumption that prediction-equivalent models produce equivalent explanations underlies many practices in explainable AI, including model selection, auditing, and regulatory evaluation. In this work, we show that this assumption does not hold. Through a large-scale empirical study across 24 datas…

• MESD: Detecting and Mitigating Procedural Bias in Intersectional Groups

  Gideon Popoola, John Sheppard · 17 mars 2026

  Research about bias in machine learning has mostly focused on outcome-oriented fairness metrics (e.g., equalized odds) and on a single protected category. Although these approaches offer great insight into bias in ML, they provide limited insight into model procedure bias. To address this gap, we pr…

• Concisely Explaining the Doubt: Minimum-Size Abductive Explanations for Linear Models with a Reject Option

  Gleilson Pedro Fernandes, Thiago Alves Rocha · 17 mars 2026

  Trustworthiness in artificial intelligence depends not only on what a model decides, but also on how it handles and explains cases in which a reliable decision cannot be made. In critical domains such as healthcare and finance, a reject option allows the model to abstain when evidence is insufficien…

• Level Up: Defining and Exploiting Transitional Problems for Curriculum Learning

  Zhenwei Tang, Amogh Inamdar, Ashton Anderson, Richard Zemel · 17 mars 2026

  Curriculum learning--ordering training examples in a sequence to aid machine learning--takes inspiration from human learning, but has not gained widespread acceptance. Static strategies for scoring item difficulty rely on indirect proxy scores of varying quality and produce curricula that are not sp…

• Universe Routing: Why Self-Evolving Agents Need Epistemic Control

  Zhaohui Geoffrey Wang · 17 mars 2026

  A critical failure mode of current lifelong agents is not lack of knowledge, but the inability to decide how to reason. When an agent encounters "Is this coin fair?" it must recognize whether to invoke frequentist hypothesis testing or Bayesian posterior inference - frameworks that are epistemologic…

• Conceptual Views of Neural Networks: A Framework for Neuro-Symbolic Analysis

  Johannes Hirth, Tom Hanika · 17 mars 2026

  We introduce \emph{conceptual views} as a formal framework grounded in Formal Concept Analysis for globally explaining neural networks. Experiments on twenty-four ImageNet models and Fruits-360 show that these views faithfully represent the original models, enable architecture comparison via Gromov-…

• The Scenic Route to Deception: Dark Patterns and Explainability Pitfalls in Conversational Navigation

  Ilya Ilyankou, Stefano Cavazzi, James Haworth · 17 mars 2026

  As pedestrian navigation increasingly experiments with Generative AI, and in particular Large Language Models, the nature of routing risks transforming from a verifiable geometric task into an opaque, persuasive dialogue. While conversational interfaces promise personalisation, they introduce risks …

• Reasoning-Grounded Natural Language Explanations for Language Models

  Vojtech Cahlik, Rodrigo Alves, Pavel Kordik · 17 mars 2026

  We propose a large language model explainability technique for obtaining faithful natural language explanations by grounding the explanations in a reasoning process. When converted to a sequence of tokens, the outputs of the reasoning process can become part of the model context and later be decoded…

• Emotional Cost Functions for AI Safety: Teaching Agents to Feel the Weight of Irreversible Consequences

  Pandurang Mopgar · 17 mars 2026

  Humans learn from catastrophic mistakes not through numerical penalties, but through qualitative suffering that reshapes who they are. Current AI safety approaches replicate none of this. Reward shaping captures magnitude, not meaning. Rule-based alignment constrains behaviour, but does not change i…

• Aumann-SHAP: The Geometry of Counterfactual Interaction Explanations in Machine Learning

  Adam Belahcen, St\'ephane Mussard · 17 mars 2026

  We introduce Aumann-SHAP, an interaction-aware framework that decomposes counterfactual transitions by restricting the model to a local hypercube connecting baseline and counterfactual features. Each hyper-cube is decomposed into a grid in order to construct an induced micro-player cooperative game …

• AssetOpsBench: Benchmarking AI Agents for Task Automation in Industrial Asset Operations and Maintenance

  Dhaval Patel, Shuxin Lin, James Rayfield, Nianjun Zhou, Chathurangi Shyalika, Suryanarayana R Yarrabothula, Roman Vaculin, Natalia Martinez, Fearghal O'donncha, Jayant Kalagnanam · 17 mars 2026

  AI for Industrial Asset Lifecycle Management aims to automate complex operational workflows, such as condition monitoring and maintenance scheduling, to minimize system downtime. While traditional AI/ML approaches solve narrow tasks in isolation, Large Language Model (LLM) agents offer a next-genera…

• Do Metrics for Counterfactual Explanations Align with User Perception?

  Felix Liedeker, Basil Ell, Philipp Cimiano, Christoph D\"using · 17 mars 2026

  Explainability is widely regarded as essential for trustworthy artificial intelligence systems. However, the metrics commonly used to evaluate counterfactual explanations are algorithmic evaluation metrics that are rarely validated against human judgments of explanation quality. This raises the ques…

• From Stochastic Answers to Verifiable Reasoning: Interpretable Decision-Making with LLM-Generated Code

  Anirudh Jaidev Mahesh, Ben Griffin, Fuat Alican, Joseph Ternasky, Zakari Salifu, Kelvin Amoaba, Yagiz Ihlamur, Aaron Ontoyin Yin, Aikins Laryea, Afriyie Samuel, Yigit Ihlamur · 17 mars 2026

  Large language models (LLMs) are increasingly used for high-stakes decision-making, yet existing approaches struggle to reconcile scalability, interpretability, and reproducibility. Black-box models obscure their reasoning, while recent LLM-based rule systems rely on per-sample evaluation, causing c…

• Incentivizing Strong Reasoning from Weak Supervision

  Yige Yuan, Teng Xiao, Shuchang Tao, Xue Wang, Jinyang Gao, Bolin Ding, Bingbing Xu · 17 mars 2026

  Large language models (LLMs) have demonstrated impressive performance on reasoning-intensive tasks, but enhancing their reasoning abilities typically relies on either reinforcement learning (RL) with verifiable signals or supervised fine-tuning (SFT) with high-quality long chain-of-thought (CoT) dem…

• xplainfi: Feature Importance and Statistical Inference for Machine Learning in R

  Lukas Burk, Fiona Katharina Ewald, Giuseppe Casalicchio, Marvin N. Wright, Bernd Bischl · 17 mars 2026

  We introduce xplainfi, an R package built on top of the mlr3 ecosystem for global, loss-based feature importance methods for machine learning models. Various feature importance methods exist in R, but significant gaps remain, particularly regarding conditional importance methods and associated stati…