Explainable Artificial Intelligence (XAI)

Derniers papiers

• Crushing the Evidence: A Dual-Penalty Evasion Framework for Fooling White-Box Explainable AI Auditors

  Niraj Kumar, Harsh Kasyap · 4 août 2026

  Post-hoc model explainers such as LIME, SHAP, and Integrated Gradients are widely deployed to audit models in high-stakes sensitive domains, including finance, healthcare, and social welfare. This ensures the model's transparency and acceptability. However, a few studies have examined potential atta…

• Tracing LLM Behavior to the Training Data with Empirical Next-Token Distributions

  Zachary Izzo · 4 août 2026

  In this paper, we study the connection between an LLM's output distribution and the data used to train it. Specifically, we study the degree to which an LLM's next-token distribution agrees with the empirical next-token distribution (ENTD) given the context in the training data. The ENTD is an appea…

• Which Modality Decides? Counterfactual Modality Attribution for Multimodal LLMs

  Vahidin Hasic, Chao Wang, Luis C. Garcia-Peraza-Herrera, David Watson, Senka Krivic · 4 août 2026

  Multimodal large language models (MLLMs) increasingly support high-stakes decision making by combining complementary information from images and text. While existing explainability methods identify influential image regions or text tokens, they cannot answer a fundamental question: which modality dr…

• Persistent Convolution: A Topological Framework for AI Alignment Testing and Semantic Space Characterization

  Tyler Ashoff, Jordan Rodu · 3 août 2026

  Modern opaque AI models prize performance over interpretability, which makes testing difficult. However, formal statistical tests conducted on a model's embedding space can provide robust characterizations of semantic structure, concept separation, and knowledge graph alignment. Model developers wou…

• A Human-Centered Validation of the Explainability-Performance Coefficient

  Christian Oliva, Luis F. Lago-Fern\'andez · 3 août 2026

  The rapid adoption of deep learning models in high-risk domains has intensified the need for trustworthy Explainable Artificial Intelligence (XAI). However, objectively evaluating explanation fidelity and aligning XAI metrics with human-centered understanding remain critical open challenges. In this…

• StaQ: a Finite Memory Approach to Discrete Action Policy Mirror Descent

  Alex Davey, Alena Shilova, Brahim Driss, Riad Akrour · 3 août 2026

  In Reinforcement Learning (RL), regularization with a Kullback-Leibler divergence that penalizes large deviations between successive policies has emerged as a popular tool both in theory and practice. This family of algorithms, often referred to as Policy Mirror Descent (PMD), has the property of av…

• A Generalized-Bayes Perspective on Counterfactual Explanations: Posterior-Based Decision-Making and Evaluation

  Keita Kinjo · 3 août 2026

  Counterfactual explanations (CEs) enhance the interpretability of machine learning models by identifying the smallest change to an input required to obtain a desired output. Although CEs are conventionally formulated as a distance-minimization problem, the theoretical basis of this formulation has r…

• Automorphism-Induced Non-Canonicity in Top-k Explanations of Graph Neural Networks

  Xin Xu, Siru Tao, Kaizhen Tan · 30 juillet 2026

  A gradient-based GNN explainer given a molecule with two chemically equivalent nitro groups assigns them attribution scores that are equal to the last bit. It cannot do otherwise: message passing is exactly permutation equivariant, so any automorphism of the input leaves every attribution invariant.…

• Behavior-Driven Explainability

  Caroline Dominik, Rolf Drechsler · 29 juillet 2026

  As system complexity has vastly increased, it has become significantly more challenging for a single person or a team to fully understand all aspects of an entire system. Particularly, this holds when considering all the different stages of a system's development life cycle, such as, e.g., design or…

• Interpretable GOHR Agents via Sparse Autoencoders

  Shiwei Tan, Yusong Zhao, Weiyi Qin, Wentian Wang, Jacob Feldman, Lazaros K. Gallos, Paul B. Kantor, Vladimir Menkov, Hao Wang · 29 juillet 2026

  A central challenge in interpreting learned decision-making systems is to determine whether their internal representations contain concepts that help explain their behavior. We report interpretability experiments for a tokenized autoregressive Transformer agent in the Game of Hidden Rules (GOHR). We…

• TaylorPODA: A Taylor Expansion-Based Method to Improve Post-Hoc Attributions for Opaque Models

  Yuchi Tang, I\~naki Esnaola, George Panoutsos · 29 juillet 2026

  Post-hoc model-agnostic local attribution (LA) methods have been widely adopted to explain opaque AI models by quantifying feature-wise contributions. However, many existing methods rely on heuristic or only partially justified attribution mechanisms, while the quality of attribution itself is often…

• Entangled by Design: Spurious Intra-Variable Signal Routing in Tabular In-Context Learners

  Athanasios Vlontzos, Giorgos Papanastasiou, Bernhard Kainz, Sotirios Tsaftaris · 29 juillet 2026

  Consider a model trained at a single hospital to predict patient recovery, where the measured feature $X$ bundles the patient's true health signal ($C$) with a systematic artefact from that hospital's equipment ($S$). Within that hospital, the artefact correlates with outcomes through unmeasured con…

• On the Design and Evaluation of Human-centered Explainable AI Systems: A Systematic Review and Taxonomy

  Aline Mangold, Juliane Zietz, Susanne Weinhold, Sebastian Pannasch · 29 juillet 2026

  As AI becomes more common in everyday living, there is an increasing demand for intelligent systems that are both performant and understandable. Explainable AI (XAI) systems aim to provide comprehensible explanations of decisions and predictions. At present, however, evaluation processes are rather …

• Sparse Autoencoders Encode Both Concepts and Functions: The Downstream Geometry of Feature Effects

  Phu Gia Hoang, Anwoy Chatterjee, Tanmoy Chakraborty, Iryna Gurevych, Subhabrata Dutta · 28 juillet 2026

  The wide-scale use of sparse autoencoders (SAEs) as interpretability tools is limited by inconsistent links between SAE features and model behavior. Features with clear activation descriptions may have weak or unexpected causal effects; steering can vary across prompts or oppose the intended directi…

• Variable Importance Identification Through Lazy Training for Binary Classification

  Anand Singh, Luke Pennella, Eshan Kabir, Xiaoxi Shen · 28 juillet 2026

  Deep neural networks have been widely used in many applications (e.g., computer vision and natural language processing); however, understanding their explainability remains a challenging task. Recently, substantial research has been devoted to improving the explainability of deep neural networks, wi…

• proxymate: Diagnosis and Adjustment of Proxy Estimates for Reliable Inference

  Alexandra N. M. Darmon, Deeksha Sinha, Steve Wilkins-Reeves, Caner Gocmen · 28 juillet 2026

  Proxy outcomes (such as short-term behavioral signals, model predictions, or surrogate endpoints) are frequently used in place of primary outcomes that are too slow to mature, rare, or challenging to measure directly. But valid inference on a proxy does not guarantee valid inference on the primary e…

• Beyond Local Inspection: Global, Guideline-Grounded Evaluation of Post-hoc XAI Methods for ECG Classification

  Nils Gumpfer, Michael Guckert, Samuel Sossalla, Birgit A{\ss}mus, Jennifer Hannig · 28 juillet 2026

  Explainable AI (XAI) is used to assess whether artificial intelligence models rely on meaningful patterns, yet explanations that appear plausible for individual predictions may systematically misrepresent model behavior. This is particularly problematic in medicine, where models may rely on irreleva…

• Same Predictions, Different Reasons: The Effect of Quantization on Model Explanations

  Kazi Kamruzzaman Rabbi, Md. Zami Al Zunaed Farabe, M. Sohel Rahman · 28 juillet 2026

  Post-training quantization (PTQ) has become a practical solution for deploying deep learning models on resource-constrained edge devices by compressing high-precision floating-point weights into low-precision representations without requiring retraining. Past research has demonstrated that quantizat…

• Extracting Algorithms in Pre-trained LLMs: A Case on Hidden Markov Models

  Yijia Dai, Zhaolin Gao, Yahya Sattar, Jennifer J. Sun, Sarah Dean · 28 juillet 2026

  Large language models (LLMs) display a striking ability to predict next observations from Hidden Markov Models (HMMs) via in-context learning (ICL), but the algorithm underlying this capability remains undetermined: prior work has proposed several candidates without consensus, and none has been grou…

• Context Is King: How In-Context Specification Shapes the Geometry of Concepts

  Elad David, Max Fomin · 28 juillet 2026

  Large language models place structured concepts on geometrically faithful manifolds: weekdays lie on a circle, months on another, usually taken to be a fixed world-model the network stores and looks up. We show that context is king: the structure a model actually uses is set by the in-context specif…

• Bounding the Causal Impact of ML-assisted Decision-Making via Counterfactual Correctness

  Jonathan Zhang, Erik Skalnes, Jacob Chen, Michael Oberst · 27 juillet 2026

  Predictive machine learning (ML) models are increasingly used to aid human decision-makers across various high-risk domains such as healthcare and criminal justice. There is a growing recognition of the need to evaluate the causal impact of deploying these systems on downstream outcomes, such as pat…

• CausalForge: A Formally Grounded, Self-Improving Agentic Framework for Automated Research in Causal Inference

  Jiyuan Tan, Vasilis Syrgkanis · 27 juillet 2026

  Automating theoretical research is constrained not only by the generation of candidate results, but also by their reliable evaluation. A common approach is to close the research loop with a large language model (LLM) reviewer. However, such reviewers remain empirically unreliable: they may accept fa…

• CEL: Comprehensive Counterfactual Explanations Library and Benchmark

  Oleksii Furman, {\L}ukasz Lenkiewicz, Marcel Musia{\l}ek, Maciej Zi\k{e}ba · 27 juillet 2026

  Counterfactual explanations are a prominent approach in explainable artificial intelligence (xAI), providing actionable guidance on what input changes would alter a model's prediction to a desired outcome. While early methods primarily focused on minimal feature changes, recent work incorporates add…

• Learning Bidirectional Causal Interactions with Heteroscedastic Neural Networks

  Masahiro Tanaka · 27 juillet 2026

  Estimating contemporaneous bidirectional interactions from observational data is difficult because each outcome is endogenous to the other, while flexible regressions may capture only reduced-form dependence. This paper proposes SEM-DNN, a heteroscedastic neural simultaneous-equation estimator that …

• Lost in Context: Addressing Context Anxiety in Large Language Models

  Ifueko Igbinedion, Jillian Ross, Etienne Ricardez, Sertac Karaman, Eric So · 27 juillet 2026

  Conventional wisdom suggests that reasoning models fail when problems exceed their capabilities. However, we find that frontier reasoning models sometimes possess the necessary capabilities to solve problems but fail due to premature self-doubt -- a phenomenon informally known as context anxiety. We…