Explainable Artificial Intelligence (XAI)

Derniers papiers

• SORTeD Rashomon Sets of Sparse Decision Trees: Anytime Enumeration

  Elif Arslan, Jacobus G. M. van der Linden, Serge Hoogendoorn, Marco Rinaldi, Emir Demirovi\'c · 6 novembre 2025

  Sparse decision tree learning provides accurate and interpretable predictive models that are ideal for high-stakes applications by finding the single most accurate tree within a (soft) size limit. Rather than relying on a single "best" tree, Rashomon sets-trees with similar performance but varying s…

• DiCoFlex: Model-agnostic diverse counterfactuals with flexible control

  Oleksii Furman, Ulvi Movsum-zada, Patryk Marszalek, Maciej Zi\k{e}ba, Marek \'Smieja · 6 novembre 2025

  Counterfactual explanations play a pivotal role in explainable artificial intelligence (XAI) by offering intuitive, human-understandable alternatives that elucidate machine learning model decisions. Despite their significance, existing methods for generating counterfactuals often require constant ac…

• RAGBoost: Efficient Retrieval-Augmented Generation with Accuracy-Preserving Context Reuse

  Yinsicheng Jiang, Yeqi Huang, Liang Cheng, Cheng Deng, Xuan Sun, Luo Mai · 6 novembre 2025

  Retrieval-augmented generation (RAG) enhances large language models (LLMs) with retrieved context but often suffers from downgraded prefill performance as modern applications demand longer and more complex inputs. Existing caching techniques either preserve accuracy with low cache reuse or improve r…

• Towards Transparent Stance Detection: A Zero-Shot Approach Using Implicit and Explicit Interpretability

  Apoorva Upadhyaya, Wolfgang Nejdl, Marco Fisichella · 6 novembre 2025

  Zero-Shot Stance Detection (ZSSD) identifies the attitude of the post toward unseen targets. Existing research using contrastive, meta-learning, or data augmentation suffers from generalizability issues or lack of coherence between text and target. Recent works leveraging large language models (LLMs…

• Unsupervised Evaluation of Multi-Turn Objective-Driven Interactions

  Emi Soroka, Tanmay Chopra, Krish Desai, Sanjay Lall · 6 novembre 2025

  Large language models (LLMs) have seen increasing popularity in enterprise applications where AI agents and humans engage in objective-driven interactions. However, these systems are difficult to evaluate: data may be complex and unlabeled; human annotation is often impractical at scale; custom metr…

• Deciphering Personalization: Towards Fine-Grained Explainability in Natural Language for Personalized Image Generation Models

  Haoming Wang, Wei Gao · 5 novembre 2025

  Image generation models are usually personalized in practical uses in order to better meet the individual users' heterogeneous needs, but most personalized models lack explainability about how they are being personalized. Such explainability can be provided via visual features in generated images, b…

• Strategic Classification with Non-Linear Classifiers

  Benyamin Trachtenberg, Nir Rosenfeld · 5 novembre 2025

  In strategic classification, the standard supervised learning setting is extended to support the notion of strategic user behavior in the form of costly feature manipulations made in response to a classifier. While standard learning supports a broad range of model classes, the study of strategic cla…

• Neural Collapse in Cumulative Link Models for Ordinal Regression: An Analysis with Unconstrained Feature Model

  Chuang Ma, Tomoyuki Obuchi, Toshiyuki Tanaka · 5 novembre 2025

  A phenomenon known as ''Neural Collapse (NC)'' in deep classification tasks, in which the penultimate-layer features and the final classifiers exhibit an extremely simple geometric structure, has recently attracted considerable attention, with the expectation that it can deepen our understanding of …

• Apriel-H1: Towards Efficient Enterprise Reasoning Models

  Oleksiy Ostapenko, Luke Kumar, Raymond Li, Denis Kocetkov, Joel Lamy-Poirier, Shruthan Radhakrishna, Soham Parikh, Shambhavi Mishra, Sebastien Paquet, Srinivas Sunkara, Val\'erie B\'ecaert, Sathwik Tejaswi Madhusudhan, Torsten Scholak · 5 novembre 2025

  Large Language Models (LLMs) achieve remarkable reasoning capabilities through transformer architectures with attention mechanisms. However, transformers suffer from quadratic time and memory complexity in the attention module (MHA) and require caching key-value states during inference, which severe…

• Scalable Evaluation and Neural Models for Compositional Generalization

  Giacomo Camposampiero, Pietro Barbiero, Michael Hersche, Roger Wattenhofer, Abbas Rahimi · 5 novembre 2025

  Compositional generalization-a key open challenge in modern machine learning-requires models to predict unknown combinations of known concepts. However, assessing compositional generalization remains a fundamental challenge due to the lack of standardized evaluation protocols and the limitations of …

• Energy-Based Model for Accurate Estimation of Shapley Values in Feature Attribution

  Cheng Lu, Jiusun Zeng, Yu Xia, Jinhui Cai, Shihua Luo · 5 novembre 2025

  Shapley value is a widely used tool in explainable artificial intelligence (XAI), as it provides a principled way to attribute contributions of input features to model outputs. However, estimation of Shapley value requires capturing conditional dependencies among all feature combinations, which pose…

• Few-Shot Multimodal Medical Imaging: A Theoretical Framework

  Md Talha Mohsin, Ismail Abdulrashid · 4 novembre 2025

  Medical imaging relies heavily on large, labeled datasets. But, unfortunately, they are not always easily accessible in clinical settings. Additionally, many practitioners often face various structural obstacles like limited data availability, fragmented data systems, and unbalanced datasets. These …

• Multi-Step Knowledge Interaction Analysis via Rank-2 Subspace Disentanglement

  Sekh Mainul Islam, Pepa Atanasova, Isabelle Augenstein · 4 novembre 2025

  Natural Language Explanations (NLEs) describe how Large Language Models (LLMs) make decisions, drawing on both external Context Knowledge (CK) and Parametric Knowledge (PK) stored in model weights. Understanding their interaction is key to assessing the grounding of NLEs, yet it remains underexplore…

• DTS: Enhancing Large Reasoning Models via Decoding Tree Sketching

  Zicheng Xu, Guanchu Wang, Yu-Neng Chuang, Guangyao Zheng, Alexander S. Szalay, Zirui Liu, Vladimir Braverman · 4 novembre 2025

  Large Reasoning Models (LRMs) demonstrate strong performance on complex reasoning tasks, yet they often suffer from overthinking, producing excessively long chain-of-thought (CoT) traces that increase inference cost and may degrade accuracy. Our analysis reveals a clear anti-correlation between reas…

• ParaScopes: What do Language Models Activations Encode About Future Text?

  Nicky Pochinkov, Yulia Volkova, Anna Vasileva, Sai V R Chereddy · 4 novembre 2025

  Interpretability studies in language models often investigate forward-looking representations of activations. However, as language models become capable of doing ever longer time horizon tasks, methods for understanding activations often remain limited to testing specific concepts or tokens. We deve…

• NeuroDeX: Unlocking Diverse Support in Decompiling Deep Neural Network Executables

  Yilin Li, Guozhu Meng, Mingyang Sun, Yanzhong Wang, Kun Sun, Hailong Chang, Yuekang Li · 4 novembre 2025

  On-device deep learning models have extensive real world demands. Deep learning compilers efficiently compile models into executables for deployment on edge devices, but these executables may face the threat of reverse engineering. Previous studies have attempted to decompile DNN executables, but th…

• Automatically Finding Rule-Based Neurons in OthelloGPT

  Aditya Singh, Zihang Wen, Srujananjali Medicherla, Adam Karvonen, Can Rager · 4 novembre 2025

  OthelloGPT, a transformer trained to predict valid moves in Othello, provides an ideal testbed for interpretability research. The model is complex enough to exhibit rich computational patterns, yet grounded in rule-based game logic that enables meaningful reverse-engineering. We present an automated…

• SpEx: A Spectral Approach to Explainable Clustering

  Tal Argov, Tal Wagner · 4 novembre 2025

  Explainable clustering by axis-aligned decision trees was introduced by Moshkovitz et al. (2020) and has gained considerable interest. Prior work has focused on minimizing the price of explainability for specific clustering objectives, lacking a general method to fit an explanation tree to any given…

• Priors in Time: Missing Inductive Biases for Language Model Interpretability

  Ekdeep Singh Lubana, Can Rager, Sai Sumedh R. Hindupur, Valerie Costa, Greta Tuckute, Oam Patel, Sonia Krishna Murthy, Thomas Fel, Daniel Wurgaft, Eric J. Bigelow, Johnny Lin, Demba Ba, Martin Wattenberg, Fernanda Viegas, Melanie Weber, Aaron Mueller · 4 novembre 2025

  Recovering meaningful concepts from language model activations is a central aim of interpretability. While existing feature extraction methods aim to identify concepts that are independent directions, it is unclear if this assumption can capture the rich temporal structure of language. Specifically,…

• ARC-GEN: A Mimetic Procedural Benchmark Generator for the Abstraction and Reasoning Corpus

  Michael D. Moffitt · 4 novembre 2025

  The Abstraction and Reasoning Corpus remains one of the most compelling and challenging benchmarks for tracking progress toward achieving Artificial General Intelligence. In contrast to other evaluation datasets designed to assess an agent's task-specific skills or accumulated knowledge, the ARC-AGI…

• LLMs are Overconfident: Evaluating Confidence Interval Calibration with FermiEval

  Elliot L. Epstein, John Winnicki, Thanawat Sornwanee, Rajat Dwaraknath · 3 novembre 2025

  Large language models (LLMs) excel at numerical estimation but struggle to correctly quantify uncertainty. We study how well LLMs construct confidence intervals around their own answers and find that they are systematically overconfident. To evaluate this behavior, we introduce FermiEval, a benchmar…

• e1: Learning Adaptive Control of Reasoning Effort

  Michael Kleinman, Matthew Trager, Alessandro Achille, Wei Xia, Stefano Soatto · 3 novembre 2025

  Increasing the thinking budget of AI models can significantly improve accuracy, but not all questions warrant the same amount of reasoning. Users may prefer to allocate different amounts of reasoning effort depending on how they value output quality versus latency and cost. To leverage this tradeoff…

• Interpretable Model-Aware Counterfactual Explanations for Random Forest

  Joshua S. Harvey, Guanchao Feng, Sai Anusha Meesala, Tina Zhao, Dhagash Mehta · 3 novembre 2025

  Despite their enormous predictive power, machine learning models are often unsuitable for applications in regulated industries such as finance, due to their limited capacity to provide explanations. While model-agnostic frameworks such as Shapley values have proved to be convenient and popular, they…

• Towards User-Focused Research in Training Data Attribution for Human-Centered Explainable AI

  Elisa Nguyen, Johannes Bertram, Evgenii Kortukov, Jean Y. Song, Seong Joon Oh · 3 novembre 2025

  Explainable AI (XAI) aims to make AI systems more transparent, yet many practices emphasise mathematical rigour over practical user needs. We propose an alternative to this model-centric approach by following a design thinking process for the emerging XAI field of training data attribution (TDA), wh…

• Towards Automated Semantic Interpretability in Reinforcement Learning via Vision-Language Models

  Zhaoxin Li, Zhang Xi-Jia, Batuhan Altundas, Letian Chen, Rohan Paleja, Matthew Gombolay · 3 novembre 2025

  Semantic interpretability in Reinforcement Learning (RL) enables transparency and verifiability of decision-making. Achieving semantic interpretability in reinforcement learning requires (1) a feature space composed of human-understandable concepts and (2) a policy that is interpretable and verifiab…