Explainable Artificial Intelligence (XAI)

Derniers papiers

• Solomonoff-Inspired Hypothesis Ranking with LLMs for Prediction Under Uncertainty

  Josh Barber (QUT), Rourke Young (QUT), Cameron Coombe (QUT,CSIRO), Will Browne (QUT) · 22 décembre 2025

  Reasoning under uncertainty is a key challenge in AI, especially for real-world tasks, where problems with sparse data demands systematic generalisation. Existing approaches struggle to balance accuracy and simplicity when evaluating multiple candidate solutions. We propose a Solomonoff-inspired met…

• PILAR: Personalizing Augmented Reality Interactions with LLM-based Human-Centric and Trustworthy Explanations for Daily Use Cases

  Ripan Kumar Kundu, Istiak Ahmed, Khaza Anuarul Hoque · 22 décembre 2025

  Artificial intelligence (AI)-driven augmented reality (AR) systems are becoming increasingly integrated into daily life, and with this growth comes a greater need for explainability in real-time user interactions. Traditional explainable AI (XAI) methods, which often rely on feature-based or example…

• Systemic Risks of Interacting AI

  Paul Darius, Thomas Hoppe, Andrei Aleksandrov · 22 décembre 2025

  In this study, we investigate system-level emergent risks of interacting AI agents. The core contribution of this work is an exploratory scenario-based identification of these risks as well as their categorization. We consider a multitude of systemic risk examples from existing literature and develo…

• Sparse, Efficient and Explainable Data Attribution with DualXDA

  Galip \"Umit Yolcu, Moritz Weckbecker, Thomas Wiegand, Wojciech Samek, Sebastian Lapuschkin · 22 décembre 2025

  Data Attribution (DA) is an emerging approach in the field of eXplainable Artificial Intelligence (XAI), aiming to identify influential training datapoints which determine model outputs. It seeks to provide transparency about the model and individual predictions, e.g. for model debugging, identifyin…

• UniCoMTE: A Universal Counterfactual Framework for Explaining Time-Series Classifiers on ECG Data

  Justin Li, Efe Sencan, Jasper Zheng Duan, Vitus J. Leung, Stephan Tsaur, Ayse K. Coskun · 22 décembre 2025

  Machine learning models, particularly deep neural networks, have demonstrated strong performance in classifying complex time series data. However, their black-box nature limits trust and adoption, especially in high-stakes domains such as healthcare. To address this challenge, we introduce UniCoMTE,…

• AdvJudge-Zero: Binary Decision Flips in LLM-as-a-Judge via Adversarial Control Tokens

  Tung-Ling Li, Yuhao Wu, Hongliang Liu · 22 décembre 2025

  Reward models and LLM-as-a-Judge systems are central to modern post-training pipelines such as RLHF, DPO, and RLAIF, where they provide scalar feedback and binary decisions that guide model selection and RL-based fine-tuning. We show that these judge systems exhibit a recurring vulnerability: short …

• Generating Samples to Probe Trained Models

  Eren Mehmet K{\i}ral, Nur\c{s}en Ayd{\i}n, \c{S}. \.Ilker Birbil · 22 décembre 2025

  There is a growing need for investigating how machine learning models operate. With this work, we aim to understand trained machine learning models by questioning their data preferences. We propose a mathematical framework that allows us to probe trained models and identify their preferred samples i…

• Imputation Uncertainty in Interpretable Machine Learning Methods

  Pegah Golchian, Marvin N. Wright · 22 décembre 2025

  In real data, missing values occur frequently, which affects the interpretation with interpretable machine learning (IML) methods. Recent work considers bias and shows that model explanations may differ between imputation methods, while ignoring additional imputation uncertainty and its influence on…

• Explanation Beyond Intuition: A Testable Criterion for Inherent Explainability

  Michael Merry, Pat Riddle, Jim Warren · 22 décembre 2025

  Inherent explainability is the gold standard in Explainable Artificial Intelligence (XAI). However, there is not a consistent definition or test to demonstrate inherent explainability. Work to date either characterises explainability through metrics, or appeals to intuition - "we know it when we see…

• Value Under Ignorance in Universal Artificial Intelligence

  Cole Wyeth, Marcus Hutter · 22 décembre 2025

  We generalize the AIXI reinforcement learning agent to admit a wider class of utility functions. Assigning a utility to each possible interaction history forces us to confront the ambiguity that some hypotheses in the agent's belief distribution only predict a finite prefix of the history, which is …

• BRAID: Bounded Reasoning for Autonomous Inference and Decisions

  Arma\u{g}an Amcalar, Eyup Cinar · 19 décembre 2025

  Large Language Models (LLMs) exhibit nonlinear relationships between performance, cost, and token usage. This paper presents a quantitative study on structured prompting using BRAID (Bounded Reasoning for Au tonomous Inference and Decisions) across multiple GPT model tiers, eval uated on the Advance…

• Exploration v.s. Exploitation: Rethinking RLVR through Clipping, Entropy, and Spurious Reward

  Peter Chen, Xiaopeng Li, Ziniu Li, Wotao Yin, Xi Chen, Tianyi Lin · 19 décembre 2025

  This paper examines the exploration-exploitation trade-off in reinforcement learning with verifiable rewards (RLVR), a framework for improving the reasoning of Large Language Models (LLMs). Recent studies suggest that RLVR can elicit strong mathematical reasoning in LLMs through two seemingly parado…

• AI Epidemiology: achieving explainable AI through expert oversight patterns

  Kit Tempest-Walters · 19 décembre 2025

  AI Epidemiology is a framework for governing and explaining advanced AI systems by applying population-level surveillance methods to AI outputs. The approach mirrors the way in which epidemiologists enable public health interventions through statistical evidence before molecular mechanisms are under…

• SALVE: Sparse Autoencoder-Latent Vector Editing for Mechanistic Control of Neural Networks

  Vegard Flovik · 19 décembre 2025

  Deep neural networks achieve impressive performance but remain difficult to interpret and control. We present SALVE (Sparse Autoencoder-Latent Vector Editing), a unified "discover, validate, and control" framework that bridges mechanistic interpretability and model editing. Using an $\ell_1$-regular…

• Foundation Models in Biomedical Imaging: Turning Hype into Reality

  Amgad Muneer, Kai Zhang, Ibraheem Hamdi, Rizwan Qureshi, Muhammad Waqas, Shereen Fouad, Hazrat Ali, Syed Muhammad Anwar, Jia Wu · 19 décembre 2025

  Foundation models (FMs) are driving a prominent shift in artificial intelligence across different domains, including biomedical imaging. These models are designed to move beyond narrow pattern recognition towards emulating sophisticated clinical reasoning, understanding complex spatial relationships…

• Explainable Ethical Assessment on Human Behaviors by Generating Conflicting Social Norms

  Yuxi Sun, Wei Gao, Hongzhan Lin, Jing Ma, Wenxuan Zhang · 19 décembre 2025

  Human behaviors are often guided or constrained by social norms, which are defined as shared, commonsense rules. For example, underlying an action ``\textit{report a witnessed crime}" are social norms that inform our conduct, such as ``\textit{It is expected to be brave to report crimes}''. Current …

• Explainable AI in Big Data Fraud Detection

  Ayush Jain, Rahul Kulkarni, Siyi Lin · 19 décembre 2025

  Big Data has become central to modern applications in finance, insurance, and cybersecurity, enabling machine learning systems to perform large-scale risk assessments and fraud detection. However, the increasing dependence on automated analytics introduces important concerns about transparency, regu…

• Conversational Time Series Foundation Models: Towards Explainable and Effective Forecasting

  Defu Cao, Michael Gee, Jinbo Liu, Hengxuan Wang, Wei Yang, Rui Wang, Yan Liu · 19 décembre 2025

  The proliferation of time series foundation models has created a landscape where no single method achieves consistent superiority, framing the central challenge not as finding the best model, but as orchestrating an optimal ensemble with interpretability. While Large Language Models (LLMs) offer pow…

• From Personalization to Prejudice: Bias and Discrimination in Memory-Enhanced AI Agents for Recruitment

  Himanshu Gharat, Himanshi Agrawal, Gourab K. Patro · 19 décembre 2025

  Large Language Models (LLMs) have empowered AI agents with advanced capabilities for understanding, reasoning, and interacting across diverse tasks. The addition of memory further enhances them by enabling continuity across interactions, learning from past experiences, and improving the relevance of…

• FedSight AI: Multi-Agent System Architecture for Federal Funds Target Rate Prediction

  Yuhan Hou, Tianji Rao, Jeremy Tan, Adler Viton, Xiyue Zhang, David Ye, Abhishek Kodi, Sanjana Dulam, Aditya Paul, Yikai Feng · 19 décembre 2025

  The Federal Open Market Committee (FOMC) sets the federal funds rate, shaping monetary policy and the broader economy. We introduce \emph{FedSight AI}, a multi-agent framework that uses large language models (LLMs) to simulate FOMC deliberations and predict policy outcomes. Member agents analyze str…

• PrivateXR: Defending Privacy Attacks in Extended Reality Through Explainable AI-Guided Differential Privacy

  Ripan Kumar Kundu, Istiak Ahmed, Khaza Anuarul Hoque · 19 décembre 2025

  The convergence of artificial AI and XR technologies (AI XR) promises innovative applications across many domains. However, the sensitive nature of data (e.g., eye-tracking) used in these systems raises significant privacy concerns, as adversaries can exploit these data and models to infer and leak …

• Activation Oracles: Training and Evaluating LLMs as General-Purpose Activation Explainers

  Adam Karvonen, James Chua, Cl\'ement Dumas, Kit Fraser-Taliente, Subhash Kantamneni, Julian Minder, Euan Ong, Arnab Sen Sharma, Daniel Wen, Owain Evans, Samuel Marks · 18 décembre 2025

  Large language model (LLM) activations are notoriously difficult to understand, with most existing techniques using complex, specialized methods for interpreting them. Recent work has proposed a simpler approach known as LatentQA: training LLMs to directly accept LLM activations as inputs and answer…

• Safer Prompts: Reducing Risks from Memorization in Visual Generative AI

  Lena Reissinger, Yuanyuan Li, Anna-Carolina Haensch, Neeraj Sarna · 18 décembre 2025

  Visual Generative AI models have demonstrated remarkable capability in generating high-quality images from user inputs like text prompts. However, because these models have billions of parameters, they risk memorizing certain parts of the training data and reproducing the memorized content. Memoriza…

• Robustness and uncertainty: two complementary aspects of the reliability of the predictions of a classifier

  Adri\'an Detavernier, Jasper De Bock · 18 décembre 2025

  We consider two conceptually different approaches for assessing the reliability of the individual predictions of a classifier: Robustness Quantification (RQ) and Uncertainty Quantification (UQ). We compare both approaches on a number of benchmark datasets and show that there is no clear winner betwe…

• Behavior Tokens Speak Louder: Disentangled Explainable Recommendation with Behavior Vocabulary

  Xinshun Feng, Mingzhe Liu, Yi Qiao, Tongyu Zhu, Leilei Sun, Shuai Wang · 18 décembre 2025

  Recent advances in explainable recommendations have explored the integration of language models to analyze natural language rationales for user-item interactions. Despite their potential, existing methods often rely on ID-based representations that obscure semantic meaning and impose structural cons…