Explainable Artificial Intelligence (XAI)

Derniers papiers

• A Controlled Counterexample to Strong Proxy-Based Explanations of OOD Performance: in a Fixed Pretraining-and-Probing Setup

  Hongmin Li · 13 mai 2026

  Task-agnostic structure proxies are often used to interpret why one pretraining corpus transfers better than another, but such explanations require the proxy to track the structure that matters for the downstream task. We test this requirement in a fixed pretraining-and-probing setup motivated by co…

• Qwen-Scope: Turning Sparse Features into Development Tools for Large Language Models

  Boyi Deng, Xu Wang, Yaoning Wang, Yu Wan, Yubo Ma, Baosong Yang, Haoran Wei, Jialong Tang, Huan Lin, Ruize Gao, Tianhao Li, Qian Cao, Xuancheng Ren, Xiaodong Deng, An Yang, Fei Huang, Dayiheng Liu, Jingren Zhou · 13 mai 2026

  Large language models have achieved remarkable capabilities across diverse tasks, yet their internal decision-making processes remain largely opaque, limiting our ability to inspect, control, and systematically improve them. This opacity motivates a growing body of research in mechanistic interpreta…

• BoolXLLM: LLM-Assisted Explainability for Boolean Models

  Du Cheng, Serdar Kadioglu, Xin Wang · 13 mai 2026

  Interpretable machine learning aims to provide transparent models whose decision-making processes can be readily understood by humans. Recent advances in rule-based approaches, such as expressive Boolean formulas (BoolXAI), offer faithful and compact representations of model behavior. However, for n…

• Multi-Narrow Transformation as a Single-Model Ensemble: Boundary Conditions, Mechanisms, and Failure Modes

  Tatsuhito Hasegawa, Taisei Tanaka · 13 mai 2026

  Single-model ensembles (SMEs) have attracted attention as a way to approximate some of the benefits of deep ensembles within a single network. However, under an approximately matched parameter budget, it remains unclear whether model capacity should be concentrated in a single wide pathway or redist…

• Partition Tree: Conditional Density Estimation over General Outcome Spaces

  Felipe Angelim, Alessandro Leite · 13 mai 2026

  We propose Partition Tree, a novel tree-based framework for conditional density estimation over general outcome spaces that supports both continuous and categorical variables within a unified formulation. Our approach models conditional distributions as piecewise-constant densities on data-adaptive …

• Towards Uncertainty-Aware Federated Granger Causal Learning

  Ayush Mohanty, Nazal Mohamed, Nagi Gebraeel · 13 mai 2026

  Granger causality recovers directed interactions from time-series data, but in many distributed systems, the data are vertically partitioned across clients, with each client observing only the variables of its own subsystem. Federated Granger causality (FedGC) recovers cross-client interactions with…

• Why Conclusions Diverge from the Same Observations: Formalizing World-Model Non-Identifiability via an Inference

  Toru Takahashi · 13 mai 2026

  When people share the same documents and observations yet reach different conclusions, the disagreement often shifts into a judgment that the other party is cognitively defective, irrational, or acting in bad faith. This paper argues that such divergence is better described as a form of non-identifi…

• Persistent and Conversational Multi-Method Explainability for Trustworthy Financial AI

  Georgios Makridis, Georgios Fatouros, John Soldatos, George Katsis, Dimosthenis Kyriazis · 13 mai 2026

  Financial institutions increasingly require AI explanations that are persistent, cross-validated across methods, and conversationally accessible to human decision-makers. We present an architecture for human-centered explainable AI in financial sentiment analysis that combines three contributions. F…

• Enhancing Multilingual Counterfactual Generation through Alignment-as-Preference Optimization

  Yilong Wang, Qianli Wang, Bohao Chu, Yihong Liu, Jing Yang, Simon Ostermann · 13 mai 2026

  Self-generated counterfactual explanations (SCEs) are minimally modified inputs (minimality) generated by large language models (LLMs) that flip their own predictions (validity), offering a causally grounded approach to unraveling black-box LLM behavior. Yet extending them beyond English remains cha…

• The Confusion is Real: GRAPHIC -- A Network Science Approach to Confusion Matrices in Deep Learning

  Johanna S. Fr\"ohlich, Bastian Heinlein, Jan U. Claar, Hans Rosenberger, Vasileios Belagiannis, Ralf R. M\"uller · 13 mai 2026

  Explainable artificial intelligence has emerged as a promising field of research to address reliability concerns in artificial intelligence. Despite significant progress in explainable artificial intelligence, few methods provide a systematic way to visualize and understand how classes are confused …

• From Model Uncertainty to Human Attention: Localization-Aware Visual Cues for Scalable Annotation Review

  Moussa Kassem Sbeyti, Joshua Holstein, Philipp Spitzer, Nadja Klein, Gerhard Satzger · 13 mai 2026

  High-quality labeled data is essential for training robust machine learning models, yet obtaining annotations at scale remains expensive. AI-assisted annotation has therefore become standard in large-scale labeling workflows. However, in tasks where model predictions carry two independent components…

• Strategically Deceptive Model Deployment in Performative Prediction

  Javier Sanguino Bautiste, Thomas Kehrenberg, Jose A. Lozano, Novi Quadrianto · 13 mai 2026

  Machine Learning systems are increasingly deployed in decision-making settings that shape user behavior and, in turn, the data on which future decisions are based. Performative Prediction (PP) formalizes this feedback loop by modeling how deployed models induce distributional shifts. It studies how …

• Interpretability Can Be Actionable

  Hadas Orgad, Fazl Barez, Tal Haklay, Isabelle Lee, Marius Mosbach, Anja Reusch, Naomi Saphra, Byron Wallace, Sarah Wiegreffe, Eric Wong, Ian Tenney, Mor Geva · 13 mai 2026

  Interpretability aims to explain the behavior of deep neural networks. Despite rapid growth, there is mounting concern that much of this work has not translated into practical impact, raising questions about its relevance and utility. This position paper argues that the central missing ingredient is…

• From Noise to Diversity: Random Embedding Injection in LLM Reasoning

  Heejun Kim, Seungpil Lee, Jewon Yeom, Jaewon Sok, Seonghyeon Park, Jeongjae Park, Taesup Kim, Sundong Kim · 13 mai 2026

  Recent soft prompt research has tried to improve reasoning by inserting trained vectors into LLM inputs, yet whether the gain comes from the learned content or from the act of injection itself has not been carefully separated. We study Random Soft Prompts (RSPs), which drop the training step entirel…

• Explaining and Breaking the Safety-Helpfulness Ceiling via Preference Dimensional Expansion

  ShiYing Huang, Liang Lin, Yuer Li, Kaiwen Luo, Zhenhong Zhou, An Zhang, Junhao Dong, Kun Wang, Zhigang Zeng · 13 mai 2026

  In the realm of multi-objective alignment for large language models, balancing disparate human preferences often manifests as a zero-sum conflict. Specifically, the intrinsic tension between competing goals dictates that aggressively optimizing for one metric (e.g., helpfulness) frequently incurs a …

• OptArgus: A Multi-Agent System to Detect Hallucinations in LLM-based Optimization Modeling

  Zhong Li, Zihan Guo, Xiaohan Lu, Juntao Wang, Jie Song, Chao Shen, Jiageng Wu, Mingyang Sun · 13 mai 2026

  Large language models (LLMs) are increasingly used to translate natural-language optimization problems into mathematical formulations and solver code, but matching the reference objective value is not a reliable test of correctness: an artifact may agree numerically while still changing the underlyi…

• OLIVIA: Online Learning via Inference-time Action Adaptation for Decision Making in LLM ReAct Agents

  Sheldon Yu, Junda Wu, Xintong Li, Nikki Lijing Kuang, Sizhe Zhou, Tong Yu, Jiawei Han, Jingbo Shang, Julian McAuley · 13 mai 2026

  Large language model agents interleave reasoning, action selection, and observation to solve sequential decision-making tasks. In deployed settings where agents repeatedly handle related multi-step tasks, small action-selection errors can accumulate into wasted tool calls, latency, and reduced relia…

• Seir\^enes: Adversarial Self-Play with Evolving Distractions for LLM Reasoning

  Chi Zhang, Haibo Qiu, Qiming Zhang, Yufei Xu, Xinbo Gao, Jing Zhang · 13 mai 2026

  We present Seir\^enes, a self-play RL framework that transforms contextual interference from a failure mode of LLM reasoning into an internal training signal for co-evolving more resilient reasoners. While RL with verifiable rewards has significantly advanced reasoning capabilities, models can still…

• ReAD: Reinforcement-Guided Capability Distillation for Large Language Models

  Xueqi Cheng, Xugui Zhou, Tyler Derr, Yushun Dong · 13 mai 2026

  Capability distillation applies knowledge distillation to selected model capabilities, aiming to compress a large language model (LLM) into a smaller one while preserving the abilities needed for a downstream task. However, most existing methods treat capabilities as independent training targets and…

• Causal Algorithmic Recourse: Foundations and Methods

  Drago Plecko, Collin Wang, Elias Bareinboim · 13 mai 2026

  The trustworthiness of AI decision-making systems is increasingly important. A key feature of such systems is the ability to provide recommendations for how an individual may reverse a negative decision, a problem known as algorithmic recourse. Existing approaches treat recourse outcomes as counterf…

• A New Technique for AI Explainability using Feature Association Map

  Sayantani Ghosh, Amit Kumar Das, Amlan Chakrabarti · 13 mai 2026

  Lack of transparency in AI systems poses challenges in critical real-life applications. It is important to be able to explain the decisions of an AI system to ensure trust on the system. Explainable AI (XAI) algorithms play a vital role in achieving this objective. In this paper, we are proposing a …

• Predicting Decisions of AI Agents from Limited Interaction through Text-Tabular Modeling

  Eilam Shapira, Moshe Tennenholtz, Roi Reichart · 13 mai 2026

  AI agents negotiate and transact in natural language with unfamiliar counterparts: a buyer bot facing an unknown seller, or a procurement assistant negotiating with a supplier. In such interactions, the counterpart's LLM, prompts, control logic, and rule-based fallbacks are hidden, while each decisi…

• Asymmetric Advantage Modulation Calibrates Entropy Dynamics in RLVR

  Hengrui Gu, Xiaotian Han, Yujing Bian, Feiyi Wang, Kaixiong Zhou · 13 mai 2026

  Reinforcement learning with verifiable rewards (RLVR) has substantially improved the reasoning ability of large language models (LLMs), but it often suffers from \textit{restricted exploration}, where the policy rapidly concentrates on a narrow set of solutions. A common remedy is entropy regulariza…

• Weakly Supervised Concept Learning for Object-centric Visual Reasoning

  Sparsh Tiwari, Bettina Finzel, Gesina Schwalbe · 12 mai 2026

  Neurosymbolic systems promise to combine deep neural network's (DNN) processing of raw sensor inputs with few-shot performance of symbolic artificial intelligence. Two-stage approaches explicitly decouple DNN based perception from subsequent rule based reasoning. This avoids optimization and interpr…

• E-TCAV: Formalizing Penultimate Proxies for Efficient Concept Based Interpretability

  Hasib Aslam, Muhammad Ali Chattha, Muhammad Taha Mukhtar, Muhammad Imran Malik, Andreas Dengel, Sheraz Ahmed · 12 mai 2026

  TCAV (Testing with Concept Activation Vectors) is an interpretability method that assesses the alignment between the internal representations of a trained neural network and human-understandable, high-level concepts. Though effective, TCAV suffers from significant computational overhead, inter-layer…