Explainable Artificial Intelligence (XAI)

Últimos artículos

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

  Ifueko Igbinedion, Jillian Ross, Etienne Ricardez, Sertac Karaman, Eric So · 27 de julio de 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…

• CEL: Comprehensive Counterfactual Explanations Library and Benchmark

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

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

  Jonathan Zhang, Erik Skalnes, Jacob Chen, Michael Oberst · 27 de julio de 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…

• Interior interpretability with attention rollout: contraction and propagation profiles in Transformers

  Umberto Biccari, Qian Huang, Enrique Zuazua · 27 de julio de 2026

  Feature-attribution methods assign scores relating input variables to a model's output, but do not by themselves characterize how explicitly defined interaction operators compose across its intermediate layers. We introduce \emph{interior interpretability}, a propagation-based perspective on interna…

• Learning Bidirectional Causal Interactions with Heteroscedastic Neural Networks

  Masahiro Tanaka · 27 de julio de 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 …

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

  Jiyuan Tan, Vasilis Syrgkanis · 27 de julio de 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…

• Gradient Concentration, Not Weight Saliency, Explains Representation-Level Class Unlearning

  Billel Habbati, Alessio Merlo, Luca Verderame, Meriem Guerar · 24 de julio de 2026

  Machine unlearning aims to remove the influence of specific training data while preserving model utility. Many state-of-the-art approaches pursue this goal by restricting the forgetting update to a subset of parameters selected through gradient-based saliency. Although such methods are widely adopte…

• Spatially Grounded Concept Bottleneck Models for Trustworthy Breast Ultrasound Diagnosis

  Moshiur Rahman Tonmoy, Dunren Che, Haitham Y. Adarbah, Afzel Noore · 24 de julio de 2026

  Concept Bottleneck Models provide interpretable-by-design predictions by mediating diagnosis through human-understandable concepts, but in medical imaging, their trustworthiness is often limited by the quality and granularity of available supervision. In particular, predicted concept activations can…

• Statistical Inference for Generative Model Comparison

  Zijun Gao, Yan Sun, Han Su · 24 de julio de 2026

  Generative models have achieved remarkable success across a range of applications, yet their evaluation still lacks principled uncertainty quantification. In this paper, we develop a method for comparing how close different generative models are to the underlying distribution of test samples. Partic…

• Uncertainty-Aware Trust Estimation for Multi-LLM Systems via Structured Expert Judgement

  Jiawei Zheng, Jiazhen Zhang · 24 de julio de 2026

  Large Language Model (LLM) ensembles are increasingly used to improve reliability by combining predictions from multiple LLMs. However, existing aggregation methods typically assume that all models are equally trustworthy, overlooking differences in uncertainty quality. This assumption is poorly sui…

• Explainability Framework for Policy-Aware Autonomous Agents

  Heather Merhout (Miami University), Daniela Inclezan (Miami University) · 24 de julio de 2026

  In the field of Artificial Intelligence, an agent is a system which is able to autonomously make decisions in order to reach a desired goal. As these systems grow more prevalent in our day-to-day lives, there has been an increased need to add explainability features which can provide an account for …

• Training Large Language Models for Self-Explanation Faithfulness

  Yeoktatt Cheah, Mar\'ia P\'erez-Ortiz, Noah Y. Siegel, Oana-Maria Camburu · 24 de julio de 2026

  We propose a Reinforcement Learning (RL) method to directly optimize the faithfulness of self-explanations - the extent to which a model's generated reasoning accurately reflects its internal decision-making process. While existing work focuses on evaluating faithfulness or using inference-time prom…

• Beyond Sufficiency: Time Series Explanation with Counterfactual Necessity

  Hongnan Ma, Yiwei Shi, Mengyue Yang, Weiru Liu · 24 de julio de 2026

  Faithful explanations of time-series classifiers should identify subsequences that are not only sufficient to preserve a black-box model's prediction, but also necessary for maintaining it. However, existing sufficiency-oriented methods can assign high importance to spurious subsequences that suppor…

• Are Single-Token Sparse Autoencoder Features Causally Necessary? Layer-Depth and SAE-Family Effects

  Seonglae Cho, Zekun Wu, Kleyton Da Costa, Rishi Kalra, Ilham Wicaksono, Adriano Koshiyama · 24 de julio de 2026

  Sparse autoencoder (SAE) features are used to interpret and steer large language models, yet whether a feature's causal role is stable across SAE families remains untested. Single-token features that activate on one vocabulary item provide the diagnostic case where ground truth permits direct compar…

• DFAH-Bench: Benchmarking Observable Agent Instability in Financial Decision-Making

  Raffi Khatchadourian · 24 de julio de 2026

  Standard evaluation benchmarks measure what a tool-using agent decides, not whether it arrives at that decision through the same process each time. We introduce DFAH-Bench, a replay benchmark that measures observable behavioral instability in financial agent decision-making across three channels -- …

• Bayesian uncertainty estimation improves clinical decision making in medical AI agents

  Frederik Hauke, Patrick Wienholt, Christiane Kuhl, Dyke Ferber, Jakob Nikolas Kather, Sven Nebelung, Daniel Truhn · 24 de julio de 2026

  Machine learning models for medical image analysis typically lack a reliable measure of confidence, limiting their use in ambiguous or atypical cases. Here we show that Monte Carlo dropout, applied to a multi-task chest-radiograph classifier (eight thoracic findings, 137,593 training images), provid…

• Euclid-MCP: A Model Context Protocol Server for Deterministic Logical Reasoning via Prolog

  Bartolomeo Bogliolo · 24 de julio de 2026

  Large Language Models (LLMs) excel at natural language understanding and generation but remain unreliable for multi-step logical reasoning, especially in safety-critical or compliance-sensitive domains. Recent neuro-symbolic approaches address this gap by coupling neural models with external symboli…

• AREX: Towards a Recursively Self-Improving Agent for Deep Research

  Shuqi Lu, Chaofan Li, Kun Luo, Zhang Zhang, Hui Wang, Hongwang Xiao, Zheng Liu, Lei Xiong, Jiahao Wang, Sen Wang, Xiyan Jiang, Wanli Li, Yuyang Hu, Hongjin Qian, Bingyu Yan, Ziyi Xia, Yingxia Shao, Kang Liu, Zhicheng Dou, Di He, Chaozhuo Li, Qiwei Ye, Zhongyuan Wang, Zheng Liu · 24 de julio de 2026

  Deep research requires agents to find answers that jointly satisfy multiple constraints. Discovering such answers is costly, whereas verifying a candidate can often be decomposed into tractable constraint-wise checks. This discovery--verification asymmetry suggests that a research agent should do mo…

• White Box Evidence Packages for Policy Audit Reports

  Seunghyun Yoo · 24 de julio de 2026

  As AI governance moves from benchmark scores toward auditable oversight, a central question is how reviewers can tell whether an LLM-generated audit report is actually supported by evidence. This paper studies that question in passage-anchored policy audits, where a report must interpret a given pol…

• Expectation Alignment of Language Models for Real-World User Expectations

  Miaomiao Li, Yang Wang, Bin Liang, Shudong Liu, Zhiwei Zhang, Kam-Fai Wong · 24 de julio de 2026

  Large language models (LLMs) have demonstrated remarkable performance on standard benchmarks, yet it remains largely unexplored whether they truly meet user expectations. Existing evaluation approaches, relying on model heuristics, expert rubrics, or user simulation, fail to capture the diversity an…

• Reliability-Aware LLM Alignment from Inconsistent Human Feedback

  Jingyi Huang, Ruohan Zong, Yujun Feng, Liran Ma, Lanyu Shang, Yang Zhang · 24 de julio de 2026

  Reinforcement Learning from Human Feedback (RLHF) is critical for aligning Large Language Models (LLMs) with human preferences. However, its efficacy is often compromised by the inherent inconsistency and subjectivity of human annotations. Existing preference optimization frameworks, such as Direct …

• Towards Faithful Graph Explanations with Synergistic Edge Effects via Granular Balls

  Jiancu Chen, Shuyin Xia, Guan Wang, Degang Chen, Fan Chen · 24 de julio de 2026

  Instance-level explanations aim to reveal the rationale behind a model's decisions for a specific graph. Previous methods explain graph neural networks (GNNs) by selecting important edges to induce subgraphs, where edge importance is assessed by perturbing each edge and observing changes in the mode…

• Scaling Interpretable Transformers with Parity Bottleneck Layers

  Andrew Mack, Kraig Yuheng Tou, Mark Henry, Zhengxun Wu, Lauren Greenspan · 24 de julio de 2026

  Language models are thought to exhibit the phenomenon of superposition, representing many more features than dimensions in their residual streams. Sparse autoencoders (SAEs) are designed to recover such features post-hoc, but training models that are interpretable by construction has remained imprac…

• When RLVR Shrinks the Reasoning Boundary: Diagnosing Pass@k Inversion

  Todd Zhou · 24 de julio de 2026

  Reinforcement learning with verifiable rewards (RLVR) can improve one-sample accuracy while making a model worse under repeated sampling. We study this pass@k inversion: after training, the policy may solve fewer distinct problems than its base model at large $k$. The failure concentrates on boundar…

• pAI-Econ-claude: A Gated Human-in-the-Loop Multi-Agent Architecture for AI-Assisted Economic Theory Development

  Chen Zhu, Xiaolu Wang, Weilong Zhang · 24 de julio de 2026

  In many social-science research tasks, such as economics, LLM-based agents must produce outputs for which no cheap, task-complete, machine-readable correctness signal exists. This creates a distinctive reliability problem for multi-agent systems: how should generation, critique, coordination, and hu…