Tagged articles
Explainable AI
34 articles · Page 1 of 1
Drawing from 23 AI projects in finance, healthcare, and government, this article reveals five high-risk model evaluation pitfalls—including overreliance on accuracy, ignoring real-world inference conditions, data drift, generic benchmarks, and lack of explainability—and provides actionable three-stage evaluation frameworks, business-specific test asset libraries, and dual-track attribution auditing methods.
AI TestingAttribution AnalysisData Drift
0 likes · 11 min read

Princeton researchers introduce QUEEN, a 4B-parameter model that combines a strong chess engine with a language model via gated cross-attention bridges, trained through a four-stage QA curriculum and iterative search distillation to achieve 2697 Elo while generating natural-language move explanations.
Explainable AILanguage ModelLeela Chess Zero
0 likes · 13 min read

XTransfer achieved 98.5% automated transaction review and 0.003% fraud rate in B2B cross-border trade by building a three-layer AI system: a B2B trade knowledge graph for data standardization, a vertical TradePilot model for document extraction and fraud detection, and an Agent assurance framework with sandbox simulation, A/B testing, and explainable AI for production deployment.
AIAgent assuranceB2B cross-border trade
0 likes · 6 min read

The article argues that increasingly precise risk scores fail to provide the contextual evidence business users need to act confidently, advocating for explainable interfaces that surface reasoning, uncertainties, and handoff clarity alongside scores, referencing NIST's trustworthy AI principles.
Explainable AINIST AI RMFUX
0 likes · 8 min read

The article analyzes how 2026 model evaluation shifts from static accuracy metrics to dynamic resilience testing, causal‑provenance data, multi‑dimensional explainable credentials, and collaborative governance, citing real‑world case studies that demonstrate dramatic reductions in failure rates and regulatory friction.
AI resilienceExplainable AIModel Evaluation
0 likes · 7 min read

The paper introduces Atomic Dance, a two‑stage framework that first discovers repeatable, semantically labeled atomic movements and then plans and completes dance sequences, achieving more coherent, rhythm‑aligned and editable music‑driven choreography, as demonstrated on the AIST++ benchmark.
Atomic MovementsChoreographyECCV 2026
0 likes · 9 min read

As AI transforms telecom networks into self-scheduling infrastructure, the key competitive advantage shifts from raw bandwidth to the ability to deliver explainable, deterministic service quality by integrating perception, prediction, and automated optimization across network, compute, and application layers.
5G-AAI in telecommunicationsEdge Computing
0 likes · 14 min read

XG-Guard introduces a novel unsupervised graph anomaly detection framework that jointly encodes sentence- and token-level features of LLM agents, leverages theme-based anomaly scoring and covariance-based score fusion to pinpoint malicious agents in multi-agent systems, providing fine-grained explanations and enabling automatic communication isolation.
Explainable AILLM securityUnsupervised Learning
0 likes · 9 min read

The article presents a detailed architecture for a high‑reliability cognitive reasoning system that combines logical inference, semantic constraints, and a seven‑layer defense to achieve efficient deduction and strict error prevention across critical domains such as medical diagnosis and financial risk control.
Explainable AIcognitive reasoninghallucination defense
0 likes · 6 min read

As AI moves into finance, healthcare, and autonomous driving, real incidents expose the limits of traditional testing, prompting a shift toward AI security testing that tackles exploding input spaces, untraceable logic, and runtime drift through adversarial robustness, fairness audits, jailbreak checks, and supply‑chain verification, all integrated into CI/CD pipelines.
AI security testingCI/CD IntegrationExplainable AI
0 likes · 8 min read

The talk introduces evidence‑mining techniques that extract supporting information from input text to improve model explainability, discusses the shortcut‑learning pitfalls of existing methods, and presents a new approach that enhances reliability and integrates with large‑model chain‑of‑thought compression for more interpretable, efficient reasoning.
AI researchExplainable AIevidence mining
0 likes · 4 min read

The article explains that a high‑accuracy model alone does not guarantee a deployable AI system; it details how inadequate evaluation leads to most production failures and presents a comprehensive, multi‑dimensional evaluation framework—including distributional robustness, fairness, explainability, temporal stability, and efficiency trade‑offs—plus practical CI/CD pipelines and common pitfalls.
AI quality assuranceCI/CDExplainable AI
0 likes · 7 min read

FaithLens is an 8‑billion‑parameter model that surpasses GPT‑4.1 and other large models on twelve hallucination‑detection benchmarks while providing high‑quality natural‑language explanations, thanks to a novel data‑synthesis pipeline, three‑dimensional filtering, and rule‑based reinforcement learning.
Explainable AILLM hallucinationefficient inference
0 likes · 12 min read

The paper introduces BLM‑Guard, an explainable multimodal ad‑moderation framework that combines interleaved‑modal chain‑of‑thought reasoning with a policy‑aligned reinforcement‑learning reward to detect hidden cross‑modal violations in short‑video ads, and presents a new benchmark that demonstrates state‑of‑the‑art performance across multiple risk scenarios.
Explainable AIPolicy Alignmentad risk detection
0 likes · 12 min read

MOF‑ChemUnity constructs a scalable, extensible knowledge graph that links millions of MOF names and synonyms to over 15,000 crystal structures using LLM‑driven entity matching, enabling accurate, explainable AI‑assisted material discovery, water‑stability prediction, expert recommendation validation, and graph‑enhanced retrieval across diverse applications.
Explainable AIGraph RAGMOF
0 likes · 17 min read

Integrating structured knowledge graphs with generative AI provides traceable, explainable, and high‑precision reasoning across domains such as medicine, finance, and law, through techniques like Retrieval‑Augmented Generation, graph neural networks, and adaptive planning, dramatically reducing hallucinations and boosting expert‑level performance.
AI HallucinationExplainable AIGraph Neural Network
0 likes · 12 min read


AIWalkerJun 24, 2025 · Artificial Intelligence
The article surveys 117 recent multimodal‑fusion papers, classifies them into improvement‑based and combination‑based approaches, highlights representative works such as TimeXL, OGP‑Net, MMR‑Mamba and FusionSight, and provides a free collection of papers, classic models and code repositories for researchers.
AI researchComputer VisionExplainable AI
0 likes · 8 min read


21CTONov 17, 2024 · Artificial Intelligence
Software developers must confront the challenges of large language models, which lack composable, testable components and transparency, raising issues of explainability, safety, legal ownership, and sustainability, and the article proposes building testable, interchangeable components to enable truly explainable AI.
AI ethicsExplainable AIcomponent testing
0 likes · 8 min read

The article details JD’s smart supply‑chain innovations, describing an explainable AI forecasting method that boosts prediction accuracy while maintaining interpretability, and an end‑to‑end inventory management model based on multi‑quantile RNNs that improves replenishment decisions, reduces costs, and enhances overall operational efficiency.
Explainable AIforecastinginventory management
0 likes · 14 min read

The Baidu Research Institute’s 2023 Paper Sharing Session featured eight cutting‑edge papers—from semi‑supervised web‑search ranking and hierarchical reinforcement learning for autonomous intersections to spatial‑heterophily graph networks, a unified XAI benchmark, differentiable neuro‑symbolic KG reasoning, and novel stochastic‑gradient and neural‑field loss analyses—showcasing advances across AI, data mining, and computer vision.
Autonomous VehiclesExplainable AINeural Fields
0 likes · 10 min read

This article examines the rapid growth of the Chinese IT operations market, explains why AIOps faces trust challenges due to opaque deep‑learning models, and presents AsiaInfo's transparent‑model and post‑hoc explanation engine together with three concrete explainable root‑cause analysis methods, concluding with future outlooks for trustworthy AIOps.
AI TrustAIOpsExplainable AI
0 likes · 13 min read

This article introduces the principles of image recognition, compares traditional logistic regression with convolutional neural networks, demonstrates their implementation using Python code, visualizes model weights, and explains key concepts such as padding, convolution, pooling, receptive fields, and multi‑layer feature extraction.
Explainable AIconvolutional neural networkimage recognition
0 likes · 12 min read

The article reviews the growing importance of model explainability in high‑risk domains, analyzes the challenges of large language models, introduces the collaborative game‑theoretic RNP framework, and presents three mitigation strategies—Folded Rationalization, Decoupled Rationalization, and Multi‑Generator Rationalization—along with experimental results and future research directions.
Collaborative RationalizationExplainable AILipschitz Continuity
0 likes · 15 min read

This article explains how uplift sensitivity prediction, Bayesian causal networks, and decision‑path construction are applied to improve insurance product, coupon, and copy recommendations on the Fliggy platform, detailing modeling approaches, evaluation metrics, and practical outcomes of the causal inference framework.
AB TestingBayesian networksExplainable AI
0 likes · 16 min read

This article introduces Explainable AI (XAI), outlines its importance, describes a step-by-step workflow, and reviews ten Python libraries—including SHAP, LIME, ELI5, Shapash, Anchors, BreakDown, Interpret‑Text, AI Explainability 360, OmniXAI, and XAI—providing usage examples and code snippets.
Explainable AIPythonmachine learning
0 likes · 12 min read

This article reviews explainable knowledge graph reasoning, covering its background, core concepts, downstream applications, major reasoning methods, motivations for interpretability, recent advances such as hierarchical and Bayesian reinforcement learning, meta‑path mining, and future research directions.
Explainable AIgraph reasoninghierarchical RL
0 likes · 18 min read

This article explains the SHAP (Shapley Additive Explanation) method, its theoretical foundations in game theory, the computation of Shapley Values, various algorithmic approximations like TreeSHAP and DeepSHAP, practical code examples, and the strengths and limitations of using SHAP for model interpretability.
Explainable AIModel InterpretationSHAP
0 likes · 11 min read

This article details the design and implementation of a transparent, explainable traffic‑decision system for an e‑commerce platform, covering background challenges, directional principles, selection and targeting methods, PV value estimation, allocation algorithms, and the supporting data‑engineering and visualization infrastructure.
Explainable AIPV estimationProduct Selection
0 likes · 22 min read


AntTechJul 18, 2022 · Artificial Intelligence
Ant Group’s security labs present a series of cutting‑edge AI research achievements—including hierarchical multi‑granular classification for computer vision, watermark‑vaccine defenses, multi‑modal document understanding, robust and explainable machine learning, and logic‑driven data‑to‑text generation—highlighting their commitment to trustworthy and secure AI applications.
AI safetyComputer VisionData2Text
0 likes · 12 min read

This article provides a comprehensive survey of model interpretability in machine learning, covering its importance, evaluation criteria, and a wide range of techniques such as permutation importance, partial dependence plots, ICE, LIME, SHAP, RETAIN, and LRP, along with practical code examples and visualizations.
Explainable AIFeature ImportanceICE
0 likes · 39 min read

This article explores why recommendation systems need reasoning, how recommendation reasoning connects to future strong AI, discusses explainability, causal inference, graph-based reasoning, and the philosophical underpinnings of AI, while also reflecting on practical examples from Hulu's recommendation platform.
Explainable AIFuture AIcausal reasoning
0 likes · 25 min read

This article explores how cognitive computing combined with graph neural networks and text generation enables large‑scale interest mining, interpretable embeddings, and multi‑modal recommendation in e‑commerce, outlining platform implementations, explainable methods, and future directions for AI‑driven consumer engagement.
Explainable AIGraph Neural Networkscognitive computing
0 likes · 9 min read

The article reviews Hulu’s 2018 iQIYI keynote on AI video applications, detailing how AI drives personalized recommendations, content analysis through computer vision and NLP, ad targeting across visual, linguistic, and semantic layers, and outlines the platform’s machine‑learning architecture and future directions.
AIExplainable AIHulu
0 likes · 6 min read


JD TechMay 24, 2018 · Artificial Intelligence
JD Security showcased its AI‑driven security research at DEF CON China, presenting three accepted papers and a collaborative AI safety report with Penn State, detailing a black‑box explanation method using Gaussian‑mixture models to make deep‑learning decisions transparent for security applications.
AIDEF CONExplainable AI
0 likes · 9 min read
